Tags

• 1999 1
• 2002 2
• 2006 2
• 2010 2
• 2012 3
• 2013 2
• 2014 5
• 2015 7
• 2016 12
• 2017 29
• 2018 32
• 2019 31
• 2020 15
• 2021 1
• 2023 1
• AAAI 1
• AAAI 2018 1
• AAMAS 1
• AAMAS 2019 1
• ACID 1
• ACL 4
• ACL 2015 1
• ACL 2016 1
• ACL 2017 2
• ACM 2
• AI 127
• Abductive Reasoning 1
• Abstract Summarization 1
• Accelerated Training 1
• Activation 1
• Activation Function 1
• Adapter 1
• Ads 2
• Adversarial 1
• Adversarial Robustness 2
• Apache 1
• Attention 7
• BASE 1
• BN 1
• Batch Normalisation 1
• BatchNorm 1
• Benchmark 1
• Big Data 4
• Build System 1
• CAP 4
• CL 9
• CTR 2
• CV 16
• CVPR 2
• CVPR 2016 1
• CVPR 2017 1
• Calibration 1
• Catastrophic Forgetting 8
• Causal Learning 2
• Causality 2
• Chemistry 1
• Classifier 1
• Click-Through Rate 2
• Clustering 2
• Compositionality 4
• Conditional Computation 1
• Container 1
• Continual Learning 10
• Contrastive 2
• Contrastive Learning 2
• Conversational Agent 1
• Count Based VQA 1
• Credit Assignment 1
• Curriculum Learning 2
• DBMS 4
• DRL 12
• Data 3
• Data Augmentation 2
• Data Mining 2
• Database 4
• Dataset 8
• Decentralized Reinforcement Learning 1
• Deep Reinforcement Learning 13
• Dependency Parsing 1
• Design Pattern 1
• Distributed Computing 3
• Distributed Reinforcement Learning 1
• Distributed SGD 1
• Distributed Systems 7
• Dynamical System 1
• EBM 2
• ECCV 1
• ECCV 2010 1
• EMNLP 6
• EMNLP 2014 1
• EMNLP 2016 2
• EMNLP 2017 2
• EMNLP 2019 1
• ERM 1
• Economics 1
• Embedding 12
• Emergent Language 1
• Empirical 4
• Empirical Advice 6
• Energy-Based Models 2
• Engineering 11
• Entropy 1
• Environment 2
• Evaluating Generalization 3
• Evaluation 3
• Explainability 1
• Exploration 1
• Factorization 1
• Finetuning 1
• GNN 6
• GPT 1
• Gating 1
• Generalizatio 1
• Generalization 6
• Generative Models 2
• Geometry 1
• Gradient Manipulation 2
• Gradient Normalization 1
• Graph 17
• Graph Neural Network 5
• Graph Representation 11
• Grounded Language Learning 1
• HRL 2
• Hierarchial RNN 1
• Hierarchical RL 1
• Hierarchical Reinforcement Learning 2
• Hybrid Models 1
• HyperNetwork 3
• Hyperbolic Embedding 2
• Hyperboloid Model 1
• Hypothesis 1
• ICCV 1
• ICCV 2015 1
• ICLR 25
• ICLR 2014 1
• ICLR 2015 1
• ICLR 2016 1
• ICLR 2017 2
• ICLR 2018 4
• ICLR 2018' 1
• ICLR 2019 8
• ICLR 2020 6
• ICLR 2021 2
• ICML 13
• ICML 2016 1
• ICML 2017 1
• ICML 2018 6
• ICML 2019 3
• ICML 2020 2
• ICML 2020' 1
• IEEE 3
• IRL 2
• ImageNet 4
• Incremental Learning 2
• Information Retrieval 2
• Information Theory 1
• Initialization 1
• Interactive Teaching 1
• Interpretability 1
• Invariance 1
• Inverse Reinforcement Learning 2
• KD 1
• KDD 4
• KDD 2013 1
• KDD 2014 1
• KDD 2015 1
• KDD 2017 1
• KRU 1
• Kernel 1
• Key Value 2
• Knowledge Distillation 1
• Knowledge Transfer 2
• Kronecker 1
• LL 6
• LLM 1
• LR 1
• Large Language Model 1
• Latency 4
• Latent Variable 2
• Learning Optimizer' 1
• Learning Rate 1
• Lifelong Learning 10
• Linear Algebra 1
• Linear Model 1
• Long-tailed Dataset 1
• Loss 2
• Loss Function 2
• MAML 3
• MANN 1
• MDP 2
• ML 3
• MPNN 1
• Machine Comprehension 4
• Machine Learning 3
• Markov Decision Process 2
• Matrix 1
• Matrix Factorization 1
• Memory 3
• Memory Augmented Neural Network 1
• Message Passing 1
• Meta Learning 8
• Meta Reinforcement Learning 1
• Mixture of Experts 1
• Model Parallelism 1
• Model-Based 5
• Model-Free 3
• Modular ML 1
• Modular Meta Learning 1
• Modular Network 1
• Module 1
• Motif 2
• Mujoco 1
• Multi Domain 1
• Multi Modal 2
• Multi Model 1
• Multi Task 5
• Multi-Agent 1
• NIPS 7
• NIPS 2014 2
• NIPS 2015 2
• NIPS 2017 3
• NIPS Workskop 1
• NLG 1
• NLI 2
• NLP 41
• NMT 2
• Natural Language Inference 3
• Natural Language Processing 12
• Network 3
• Network Embedding 1
• NeurIPS 6
• NeurIPS 2018 3
• NeurIPS 2019 2
• NeurIPS 2020 2
• NeurIPS Workshop 2018 1
• Neural Computation 1
• Neural Computation 2002 1
• Neural Machine Translation 1
• Neural Message Passing 1
• Neural Module Network 1
• Neurips 3
• Neurips 2018 1
• Neurips 2019 2
• Normalization 1
• OPT 1
• OS 1
• Object-Oriented Learning 2
• Off policy RL 3
• One shot learning 1
• Online Learning 1
• Operating Systems 1
• Optimizer 1
• Out of Distribution 2
• Out of Distribution Detection 1
• Out of Vocabulary Words 1
• Outlier Detection 1
• POS 1
• Physical Reasoning 1
• Physics 2
• Planning 2
• Poincare Ball Model 2
• Pointer Network 1
• Pooling 1
• PreTrained Langauge Model 1
• Pretraining 2
• Procedural Text 1
• Pruning Network 1
• QA 7
• RL 29
• RNN 4
• RRL 1
• Ranking 1
• Reasoning 3
• Recommender 1
• Recommender Systems 1
• Recurrent Neural Network 2
• Reinforcement Learning 23
• Relation Learning 3
• Relational Inference 1
• Relational Learning 5
• Relational Network 1
• Replay Buffer 5
• Representation Analysis 1
• Representation Learning 4
• Robustness 2
• SAT 1
• SGD 1
• SOTA 9
• SSL 1
• SSO 1
• SWA 1
• Sample Efficient 2
• Scale 12
• Science 2
• Science 2002 1
• Science 2016 1
• Self Gated 1
• Self Supervised 2
• Semantic Loss 1
• Sentiment Analysis 1
• Seq2Seq 1
• Sequential models 1
• Set 1
• Siamese 1
• Softmax 2
• Software 4
• Software Engineering 5
• Speech 1
• State Abstraction 1
• Stochastic Gradient Descent 1
• Structured Exploration 1
• Summarization 1
• Symbolic Knowledge 1
• Synchronous SGD 1
• Systems 11
• Technical Debt 1
• Text-to-Text Transformer 1
• Theory 2
• Transfer Learning 7
• Transformer 3
• Tree 1
• Tucker Decomposition 1
• UAI 1
• UAI 2018 1
• USENIX 2
• Unsupervised 6
• VAE 1
• VQA 6
• Virtual Embodiment 1
• WACV 1
• WACV 2017 1
• Weight Adaptation 1
• Word Vectors 3
• Workshop 2
• Zero Shot Generalization 1
• Zero-Shot 1

1999

• September 21, 2020 » Harvest, Yield, and Scalable Tolerant Systems

2002

• May 14, 2019 » Multiple Model-Based Reinforcement Learning
• November 12, 2017 » Network Motifs - Simple Building Blocks of Complex Networks

2006

• November 16, 2020 » Data Management for Internet-Scale Single-Sign-On
• December 26, 2019 » Towards a Unified Theory of State Abstraction for MDPs

2010

• December 14, 2020 » Cassandra - a decentralized structured storage system
• March 05, 2020 » What Does Classifying More Than 10,000 Image Categories Tell Us?

2012

• December 07, 2020 » CAP twelve years later - How the rules have changed
• November 30, 2020 » Consistency Tradeoffs in Modern Distributed Database System Design
• November 09, 2020 » Searching for Build Debt - Experiences Managing Technical Debt at Google

2013

• March 15, 2021 » The Tail at Scale
• March 01, 2021 » Ad Click Prediction - a View from the Trenches

2014

• March 08, 2021 » Practical Lessons from Predicting Clicks on Ads at Facebook
• March 05, 2018 » An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks
• January 06, 2018 » How transferable are features in deep neural networks
• December 31, 2017 » Distilling the Knowledge in a Neural Network
• June 03, 2017 » A Fast and Accurate Dependency Parser using Neural Networks

2015

• January 14, 2018 » Exploring Models and Data for Image Question Answering
• December 24, 2017 » PTE - Predictive Text Embedding through Large-scale Heterogeneous Text Networks
• November 05, 2017 » Word Representations via Gaussian Embedding
• August 27, 2017 » Pointer Networks
• June 26, 2017 » Two/Too Simple Adaptations of Word2Vec for Syntax Problems
• April 28, 2017 » Simple Baseline for Visual Question Answering
• April 27, 2017 » VQA-Visual Question Answering

2016

• March 22, 2021 » Deep Neural Networks for YouTube Recommendations
• January 25, 2021 » HyperNetworks
• December 21, 2020 » Design patterns for container-based distributed systems
• October 25, 2018 » One-shot Learning with Memory-Augmented Neural Networks
• May 21, 2018 » Net2Net-Accelerating Learning via Knowledge Transfer
• March 11, 2018 » Improving Information Extraction by Acquiring External Evidence with Reinforcement Learning
• February 11, 2018 » Stylistic Transfer in Natural Language Generation Systems Using Recurrent Neural Networks
• December 11, 2017 » Revisiting Semi-Supervised Learning with Graph Embeddings
• November 19, 2017 » Higher-order organization of complex networks
• July 09, 2017 » Ask Me Anything - Dynamic Memory Networks for Natural Language Processing
• June 17, 2017 » A Decomposable Attention Model for Natural Language Inference
• May 23, 2017 » Neural Module Networks

2017

• August 14, 2020 » Outrageously Large Neural Networks--The Sparsely-Gated Mixture-of-Experts Layer
• July 30, 2020 » GradNorm--Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks
• February 27, 2020 » mixup - Beyond Empirical Risk Minimization
• January 09, 2020 » Accurate, Large Minibatch SGD - Training ImageNet in 1 Hour
• February 05, 2019 » Linguistic Knowledge as Memory for Recurrent Neural Networks
• December 18, 2018 » Hindsight Experience Replay
• November 01, 2018 » Learned Optimizers that Scale and Generalize
• October 11, 2018 » Poincaré Embeddings for Learning Hierarchical Representations
• September 27, 2018 » HoME - a Household Multimodal Environment
• August 08, 2018 » Imagination-Augmented Agents for Deep Reinforcement Learning
• April 08, 2018 » Neural Message Passing for Quantum Chemistry
• April 02, 2018 » Unsupervised Learning by Predicting Noise
• March 18, 2018 » Cyclical Learning Rates for Training Neural Networks
• February 05, 2018 » Get To The Point - Summarization with Pointer-Generator Networks
• January 29, 2018 » StarSpace - Embed All The Things!
• January 22, 2018 » Emotional Chatting Machine - Emotional Conversation Generation with Internal and External Memory
• November 28, 2017 » Two-Stage Synthesis Networks for Transfer Learning in Machine Comprehension
• October 28, 2017 » HARP - Hierarchical Representation Learning for Networks
• October 22, 2017 » Swish - a Self-Gated Activation Function
• October 15, 2017 » Reading Wikipedia to Answer Open-Domain Questions
• October 01, 2017 » Task-Oriented Query Reformulation with Reinforcement Learning
• September 22, 2017 » Refining Source Representations with Relation Networks for Neural Machine Translation
• August 21, 2017 » Learning to Compute Word Embeddings On the Fly
• August 07, 2017 » R-NET - Machine Reading Comprehension with Self-matching Networks
• July 24, 2017 » ReasoNet - Learning to Stop Reading in Machine Comprehension
• July 17, 2017 » Principled Detection of Out-of-Distribution Examples in Neural Networks
• July 01, 2017 » One Model To Learn Them All
• May 14, 2017 » Making the V in VQA Matter - Elevating the Role of Image Understanding in Visual Question Answering
• May 07, 2017 » Conditional Similarity Networks

2018

• March 29, 2021 » Synthesized Policies for Transfer and Adaptation across Tasks and Environments
• January 11, 2021 » GPipe - Easy Scaling with Micro-Batch Pipeline Parallelism
• August 31, 2020 » Deep Reinforcement Learning and the Deadly Triad
• July 16, 2020 » Averaging Weights leads to Wider Optima and Better Generalization
• March 12, 2020 » Competitive Training of Mixtures of Independent Deep Generative Models
• September 05, 2019 » How to train your MAML
• August 08, 2019 » Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models
• August 01, 2019 » Assessing Generalization in Deep Reinforcement Learning
• July 25, 2019 » Quantifying Generalization in Reinforcement Learning
• July 18, 2019 » Set Transformer - A Framework for Attention-based Permutation-Invariant Neural Networks
• June 27, 2019 » Measuring abstract reasoning in neural networks
• June 08, 2019 » Meta-Reinforcement Learning of Structured Exploration Strategies
• June 01, 2019 » Relational Reinforcement Learning
• April 09, 2019 » Towards a natural benchmark for continual learning
• April 02, 2019 » Meta-Learning Update Rules for Unsupervised Representation Learning
• January 22, 2019 » Modular meta-learning
• January 02, 2019 » Pre-training Graph Neural Networks with Kernels
• December 25, 2018 » Smooth Loss Functions for Deep Top-k Classification
• December 11, 2018 » Representation Tradeoffs for Hyperbolic Embeddings
• October 18, 2018 » BabyAI - First Steps Towards Grounded Language Learning With a Human In the Loop
• October 04, 2018 » When Recurrent Models Don’t Need To Be Recurrent
• September 12, 2018 » Emergence of Grounded Compositional Language in Multi-Agent Populations
• August 21, 2018 » A Semantic Loss Function for Deep Learning with Symbolic Knowledge
• August 16, 2018 » Hierarchical Graph Representation Learning with Differentiable Pooling
• July 19, 2018 » Kronecker Recurrent Units
• July 11, 2018 » Learning Independent Causal Mechanisms
• July 04, 2018 » Memory-based Parameter Adaptation
• June 09, 2018 » Born Again Neural Networks
• May 06, 2018 » Learning to Count Objects in Natural Images for Visual Question Answering
• March 25, 2018 » The Lottery Ticket Hypothesis - Training Pruned Neural Networks
• February 24, 2018 » Learning an SAT Solver from Single-Bit Supervision
• February 17, 2018 » Neural Relational Inference for Interacting Systems

2019

• February 08, 2021 » Continual learning with hypernetworks
• September 14, 2020 » MONet - Unsupervised Scene Decomposition and Representation
• August 06, 2020 » Gradient Surgery for Multi-Task Learning
• July 02, 2020 » When to use parametric models in reinforcement learning?
• June 25, 2020 » Network Randomization - A Simple Technique for Generalization in Deep Reinforcement Learning
• June 18, 2020 » On the Difficulty of Warm-Starting Neural Network Training
• February 20, 2020 » ELECTRA - Pre-training Text Encoders as Discriminators Rather Than Generators
• February 13, 2020 » Gradient based sample selection for online continual learning
• February 06, 2020 » Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One
• January 30, 2020 » Massively Multilingual Neural Machine Translation in the Wild - Findings and Challenges
• January 23, 2020 » Observational Overfitting in Reinforcement Learning
• January 16, 2020 » Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML
• January 02, 2020 » Superposition of many models into one
• December 19, 2019 » ALBERT - A Lite BERT for Self-supervised Learning of Language Representations
• December 12, 2019 » Everything Happens for a Reason - Discovering the Purpose of Actions in Procedural Text
• December 05, 2019 » Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
• November 28, 2019 » Contrastive Learning of Structured World Models
• September 12, 2019 » Gossip based Actor-Learner Architectures for Deep RL
• August 29, 2019 » PHYRE - A New Benchmark for Physical Reasoning
• August 22, 2019 » Large Memory Layers with Product Keys
• August 15, 2019 » Abductive Commonsense Reasoning
• June 20, 2019 » Hamiltonian Neural Networks
• June 13, 2019 » Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations
• May 21, 2019 » Good-Enough Compositional Data Augmentation
• March 26, 2019 » GNN Explainer - A Tool for Post-hoc Explanation of Graph Neural Networks
• March 16, 2019 » To Tune or Not to Tune? Adapting Pretrained Representations to Diverse Tasks
• March 12, 2019 » Model Primitive Hierarchical Lifelong Reinforcement Learning
• February 19, 2019 » TuckER - Tensor Factorization for Knowledge Graph Completion
• January 29, 2019 » Diversity is All You Need - Learning Skills without a Reward Function
• January 15, 2019 » Hierarchical RL Using an Ensemble of Proprioceptive Periodic Policies
• January 08, 2019 » Efficient Lifelong Learning with A-GEM

2020

• February 22, 2021 » Anatomy of Catastrophic Forgetting - Hidden Representations and Task Semantics
• February 15, 2021 » When Do Curricula Work?
• January 18, 2021 » Energy-based Models for Continual Learning
• January 04, 2021 » Compositional Explanations of Neurons
• November 23, 2020 » Exploring Simple Siamese Representation Learning
• November 02, 2020 » One Solution is Not All You Need - Few-Shot Extrapolation via Structured MaxEnt RL
• October 19, 2020 » Learning Explanations That Are Hard To Vary
• October 12, 2020 » Remembering for the Right Reasons - Explanations Reduce Catastrophic Forgetting
• September 28, 2020 » A Foliated View of Transfer Learning
• September 07, 2020 » Revisiting Fundamentals of Experience Replay
• August 24, 2020 » Alpha Net--Adaptation with Composition in Classifier Space
• July 23, 2020 » TaskNorm--Rethinking Batch Normalization for Meta-Learning
• July 09, 2020 » Decentralized Reinforcement Learning -- Global Decision-Making via Local Economic Transactions
• April 30, 2020 » Supervised Contrastive Learning
• April 09, 2020 » CURL - Contrastive Unsupervised Representations for Reinforcement Learning

2021

• February 01, 2021 » Zero-shot Learning by Generating Task-specific Adapters

2023

• February 10, 2023 » Toolformer - Language Models Can Teach Themselves to Use Tools

AAAI

• September 12, 2018 » Emergence of Grounded Compositional Language in Multi-Agent Populations

AAAI 2018

• September 12, 2018 » Emergence of Grounded Compositional Language in Multi-Agent Populations

AAMAS

• March 12, 2019 » Model Primitive Hierarchical Lifelong Reinforcement Learning

AAMAS 2019

• March 12, 2019 » Model Primitive Hierarchical Lifelong Reinforcement Learning

ACID

• December 07, 2020 » CAP twelve years later - How the rules have changed

ACL

• February 11, 2018 » Stylistic Transfer in Natural Language Generation Systems Using Recurrent Neural Networks
• February 05, 2018 » Get To The Point - Summarization with Pointer-Generator Networks
• October 15, 2017 » Reading Wikipedia to Answer Open-Domain Questions
• June 26, 2017 » Two/Too Simple Adaptations of Word2Vec for Syntax Problems

ACL 2015

• June 26, 2017 » Two/Too Simple Adaptations of Word2Vec for Syntax Problems

ACL 2016

• February 11, 2018 » Stylistic Transfer in Natural Language Generation Systems Using Recurrent Neural Networks

ACL 2017

• February 05, 2018 » Get To The Point - Summarization with Pointer-Generator Networks
• October 15, 2017 » Reading Wikipedia to Answer Open-Domain Questions

ACM

• March 22, 2021 » Deep Neural Networks for YouTube Recommendations
• March 15, 2021 » The Tail at Scale

AI

• February 10, 2023 » Toolformer - Language Models Can Teach Themselves to Use Tools
• March 29, 2021 » Synthesized Policies for Transfer and Adaptation across Tasks and Environments
• February 22, 2021 » Anatomy of Catastrophic Forgetting - Hidden Representations and Task Semantics
• February 15, 2021 » When Do Curricula Work?
• February 08, 2021 » Continual learning with hypernetworks
• February 01, 2021 » Zero-shot Learning by Generating Task-specific Adapters
• January 25, 2021 » HyperNetworks
• January 18, 2021 » Energy-based Models for Continual Learning
• January 11, 2021 » GPipe - Easy Scaling with Micro-Batch Pipeline Parallelism
• January 04, 2021 » Compositional Explanations of Neurons
• November 23, 2020 » Exploring Simple Siamese Representation Learning
• November 02, 2020 » One Solution is Not All You Need - Few-Shot Extrapolation via Structured MaxEnt RL
• October 19, 2020 » Learning Explanations That Are Hard To Vary
• October 12, 2020 » Remembering for the Right Reasons - Explanations Reduce Catastrophic Forgetting
• September 28, 2020 » A Foliated View of Transfer Learning
• September 14, 2020 » MONet - Unsupervised Scene Decomposition and Representation
• September 07, 2020 » Revisiting Fundamentals of Experience Replay
• August 31, 2020 » Deep Reinforcement Learning and the Deadly Triad
• August 24, 2020 » Alpha Net--Adaptation with Composition in Classifier Space
• August 14, 2020 » Outrageously Large Neural Networks--The Sparsely-Gated Mixture-of-Experts Layer
• August 06, 2020 » Gradient Surgery for Multi-Task Learning
• July 30, 2020 » GradNorm--Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks
• July 23, 2020 » TaskNorm--Rethinking Batch Normalization for Meta-Learning
• July 16, 2020 » Averaging Weights leads to Wider Optima and Better Generalization
• July 09, 2020 » Decentralized Reinforcement Learning -- Global Decision-Making via Local Economic Transactions
• July 02, 2020 » When to use parametric models in reinforcement learning?
• June 25, 2020 » Network Randomization - A Simple Technique for Generalization in Deep Reinforcement Learning
• June 18, 2020 » On the Difficulty of Warm-Starting Neural Network Training
• April 30, 2020 » Supervised Contrastive Learning
• April 09, 2020 » CURL - Contrastive Unsupervised Representations for Reinforcement Learning
• March 12, 2020 » Competitive Training of Mixtures of Independent Deep Generative Models
• March 05, 2020 » What Does Classifying More Than 10,000 Image Categories Tell Us?
• February 27, 2020 » mixup - Beyond Empirical Risk Minimization
• February 20, 2020 » ELECTRA - Pre-training Text Encoders as Discriminators Rather Than Generators
• February 13, 2020 » Gradient based sample selection for online continual learning
• February 06, 2020 » Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One
• January 30, 2020 » Massively Multilingual Neural Machine Translation in the Wild - Findings and Challenges
• January 23, 2020 » Observational Overfitting in Reinforcement Learning
• January 16, 2020 » Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML
• January 09, 2020 » Accurate, Large Minibatch SGD - Training ImageNet in 1 Hour
• January 02, 2020 » Superposition of many models into one
• December 26, 2019 » Towards a Unified Theory of State Abstraction for MDPs
• December 19, 2019 » ALBERT - A Lite BERT for Self-supervised Learning of Language Representations
• December 12, 2019 » Everything Happens for a Reason - Discovering the Purpose of Actions in Procedural Text
• December 05, 2019 » Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
• November 28, 2019 » Contrastive Learning of Structured World Models
• September 12, 2019 » Gossip based Actor-Learner Architectures for Deep RL
• September 05, 2019 » How to train your MAML
• August 29, 2019 » PHYRE - A New Benchmark for Physical Reasoning
• August 22, 2019 » Large Memory Layers with Product Keys
• August 15, 2019 » Abductive Commonsense Reasoning
• August 08, 2019 » Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models
• August 01, 2019 » Assessing Generalization in Deep Reinforcement Learning
• July 25, 2019 » Quantifying Generalization in Reinforcement Learning
• July 18, 2019 » Set Transformer - A Framework for Attention-based Permutation-Invariant Neural Networks
• June 27, 2019 » Measuring abstract reasoning in neural networks
• June 20, 2019 » Hamiltonian Neural Networks
• June 13, 2019 » Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations
• June 08, 2019 » Meta-Reinforcement Learning of Structured Exploration Strategies
• June 01, 2019 » Relational Reinforcement Learning
• May 21, 2019 » Good-Enough Compositional Data Augmentation
• May 14, 2019 » Multiple Model-Based Reinforcement Learning
• April 09, 2019 » Towards a natural benchmark for continual learning
• April 02, 2019 » Meta-Learning Update Rules for Unsupervised Representation Learning
• March 26, 2019 » GNN Explainer - A Tool for Post-hoc Explanation of Graph Neural Networks
• March 16, 2019 » To Tune or Not to Tune? Adapting Pretrained Representations to Diverse Tasks
• March 12, 2019 » Model Primitive Hierarchical Lifelong Reinforcement Learning
• February 19, 2019 » TuckER - Tensor Factorization for Knowledge Graph Completion
• February 05, 2019 » Linguistic Knowledge as Memory for Recurrent Neural Networks
• January 15, 2019 » Hierarchical RL Using an Ensemble of Proprioceptive Periodic Policies
• January 08, 2019 » Efficient Lifelong Learning with A-GEM
• January 02, 2019 » Pre-training Graph Neural Networks with Kernels
• December 25, 2018 » Smooth Loss Functions for Deep Top-k Classification
• December 18, 2018 » Hindsight Experience Replay
• December 11, 2018 » Representation Tradeoffs for Hyperbolic Embeddings
• November 01, 2018 » Learned Optimizers that Scale and Generalize
• October 25, 2018 » One-shot Learning with Memory-Augmented Neural Networks
• October 18, 2018 » BabyAI - First Steps Towards Grounded Language Learning With a Human In the Loop
• October 11, 2018 » Poincaré Embeddings for Learning Hierarchical Representations
• October 04, 2018 » When Recurrent Models Don’t Need To Be Recurrent
• September 27, 2018 » HoME - a Household Multimodal Environment
• September 12, 2018 » Emergence of Grounded Compositional Language in Multi-Agent Populations
• August 21, 2018 » A Semantic Loss Function for Deep Learning with Symbolic Knowledge
• August 16, 2018 » Hierarchical Graph Representation Learning with Differentiable Pooling
• August 08, 2018 » Imagination-Augmented Agents for Deep Reinforcement Learning
• July 19, 2018 » Kronecker Recurrent Units
• July 11, 2018 » Learning Independent Causal Mechanisms
• July 04, 2018 » Memory-based Parameter Adaptation
• June 09, 2018 » Born Again Neural Networks
• May 21, 2018 » Net2Net-Accelerating Learning via Knowledge Transfer
• May 06, 2018 » Learning to Count Objects in Natural Images for Visual Question Answering
• April 08, 2018 » Neural Message Passing for Quantum Chemistry
• April 02, 2018 » Unsupervised Learning by Predicting Noise
• March 25, 2018 » The Lottery Ticket Hypothesis - Training Pruned Neural Networks
• March 18, 2018 » Cyclical Learning Rates for Training Neural Networks
• March 11, 2018 » Improving Information Extraction by Acquiring External Evidence with Reinforcement Learning
• March 05, 2018 » An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks
• February 24, 2018 » Learning an SAT Solver from Single-Bit Supervision
• February 17, 2018 » Neural Relational Inference for Interacting Systems
• February 11, 2018 » Stylistic Transfer in Natural Language Generation Systems Using Recurrent Neural Networks
• February 05, 2018 » Get To The Point - Summarization with Pointer-Generator Networks
• January 22, 2018 » Emotional Chatting Machine - Emotional Conversation Generation with Internal and External Memory
• January 14, 2018 » Exploring Models and Data for Image Question Answering
• January 06, 2018 » How transferable are features in deep neural networks
• December 31, 2017 » Distilling the Knowledge in a Neural Network
• December 11, 2017 » Revisiting Semi-Supervised Learning with Graph Embeddings
• November 28, 2017 » Two-Stage Synthesis Networks for Transfer Learning in Machine Comprehension
• November 05, 2017 » Word Representations via Gaussian Embedding
• October 28, 2017 » HARP - Hierarchical Representation Learning for Networks
• October 22, 2017 » Swish - a Self-Gated Activation Function
• October 15, 2017 » Reading Wikipedia to Answer Open-Domain Questions
• October 01, 2017 » Task-Oriented Query Reformulation with Reinforcement Learning
• September 22, 2017 » Refining Source Representations with Relation Networks for Neural Machine Translation
• August 27, 2017 » Pointer Networks
• August 21, 2017 » Learning to Compute Word Embeddings On the Fly
• August 07, 2017 » R-NET - Machine Reading Comprehension with Self-matching Networks
• July 24, 2017 » ReasoNet - Learning to Stop Reading in Machine Comprehension
• July 17, 2017 » Principled Detection of Out-of-Distribution Examples in Neural Networks
• July 09, 2017 » Ask Me Anything - Dynamic Memory Networks for Natural Language Processing
• July 01, 2017 » One Model To Learn Them All
• June 26, 2017 » Two/Too Simple Adaptations of Word2Vec for Syntax Problems
• June 17, 2017 » A Decomposable Attention Model for Natural Language Inference
• May 23, 2017 » Neural Module Networks
• May 14, 2017 » Making the V in VQA Matter - Elevating the Role of Image Understanding in Visual Question Answering
• May 07, 2017 » Conditional Similarity Networks
• April 28, 2017 » Simple Baseline for Visual Question Answering
• April 27, 2017 » VQA-Visual Question Answering

Abductive Reasoning

• August 15, 2019 » Abductive Commonsense Reasoning

Abstract Summarization

• February 05, 2018 » Get To The Point - Summarization with Pointer-Generator Networks

Accelerated Training

• March 18, 2018 » Cyclical Learning Rates for Training Neural Networks

Activation

• March 05, 2018 » An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks

Activation Function

• October 22, 2017 » Swish - a Self-Gated Activation Function

Adapter

• February 01, 2021 » Zero-shot Learning by Generating Task-specific Adapters

Ads

• March 08, 2021 » Practical Lessons from Predicting Clicks on Ads at Facebook
• March 01, 2021 » Ad Click Prediction - a View from the Trenches

Adversarial

• February 06, 2020 » Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One

Adversarial Robustness

• February 27, 2020 » mixup - Beyond Empirical Risk Minimization
• February 06, 2020 » Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One

Apache

• December 14, 2020 » Cassandra - a decentralized structured storage system

Attention

• September 14, 2020 » MONet - Unsupervised Scene Decomposition and Representation
• February 20, 2020 » ELECTRA - Pre-training Text Encoders as Discriminators Rather Than Generators
• December 19, 2019 » ALBERT - A Lite BERT for Self-supervised Learning of Language Representations
• August 22, 2019 » Large Memory Layers with Product Keys
• July 09, 2017 » Ask Me Anything - Dynamic Memory Networks for Natural Language Processing
• July 01, 2017 » One Model To Learn Them All
• June 17, 2017 » A Decomposable Attention Model for Natural Language Inference

BASE

• December 07, 2020 » CAP twelve years later - How the rules have changed

BN

• July 23, 2020 » TaskNorm--Rethinking Batch Normalization for Meta-Learning

Batch Normalisation

• July 23, 2020 » TaskNorm--Rethinking Batch Normalization for Meta-Learning

BatchNorm

• July 23, 2020 » TaskNorm--Rethinking Batch Normalization for Meta-Learning

Benchmark

• August 29, 2019 » PHYRE - A New Benchmark for Physical Reasoning

Big Data

• December 14, 2020 » Cassandra - a decentralized structured storage system
• December 07, 2020 » CAP twelve years later - How the rules have changed
• November 30, 2020 » Consistency Tradeoffs in Modern Distributed Database System Design
• November 16, 2020 » Data Management for Internet-Scale Single-Sign-On

Build System

• November 09, 2020 » Searching for Build Debt - Experiences Managing Technical Debt at Google

CAP

• December 14, 2020 » Cassandra - a decentralized structured storage system
• December 07, 2020 » CAP twelve years later - How the rules have changed
• November 30, 2020 » Consistency Tradeoffs in Modern Distributed Database System Design
• September 21, 2020 » Harvest, Yield, and Scalable Tolerant Systems

CL

• February 22, 2021 » Anatomy of Catastrophic Forgetting - Hidden Representations and Task Semantics
• February 08, 2021 » Continual learning with hypernetworks
• January 18, 2021 » Energy-based Models for Continual Learning
• October 12, 2020 » Remembering for the Right Reasons - Explanations Reduce Catastrophic Forgetting
• February 13, 2020 » Gradient based sample selection for online continual learning
• January 02, 2020 » Superposition of many models into one
• April 09, 2019 » Towards a natural benchmark for continual learning
• March 12, 2019 » Model Primitive Hierarchical Lifelong Reinforcement Learning
• January 08, 2019 » Efficient Lifelong Learning with A-GEM

CTR

• March 08, 2021 » Practical Lessons from Predicting Clicks on Ads at Facebook
• March 01, 2021 » Ad Click Prediction - a View from the Trenches

CV

• November 23, 2020 » Exploring Simple Siamese Representation Learning
• September 14, 2020 » MONet - Unsupervised Scene Decomposition and Representation
• March 05, 2020 » What Does Classifying More Than 10,000 Image Categories Tell Us?
• January 08, 2019 » Efficient Lifelong Learning with A-GEM
• May 21, 2018 » Net2Net-Accelerating Learning via Knowledge Transfer
• May 06, 2018 » Learning to Count Objects in Natural Images for Visual Question Answering
• April 02, 2018 » Unsupervised Learning by Predicting Noise
• January 14, 2018 » Exploring Models and Data for Image Question Answering
• January 06, 2018 » How transferable are features in deep neural networks
• July 17, 2017 » Principled Detection of Out-of-Distribution Examples in Neural Networks
• July 01, 2017 » One Model To Learn Them All
• May 23, 2017 » Neural Module Networks
• May 14, 2017 » Making the V in VQA Matter - Elevating the Role of Image Understanding in Visual Question Answering
• May 07, 2017 » Conditional Similarity Networks
• April 28, 2017 » Simple Baseline for Visual Question Answering
• April 27, 2017 » VQA-Visual Question Answering

CVPR

• May 23, 2017 » Neural Module Networks
• May 07, 2017 » Conditional Similarity Networks

CVPR 2016

• May 23, 2017 » Neural Module Networks

CVPR 2017

• May 07, 2017 » Conditional Similarity Networks

Calibration

• February 06, 2020 » Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One

Catastrophic Forgetting

• February 22, 2021 » Anatomy of Catastrophic Forgetting - Hidden Representations and Task Semantics
• January 18, 2021 » Energy-based Models for Continual Learning
• October 12, 2020 » Remembering for the Right Reasons - Explanations Reduce Catastrophic Forgetting
• February 13, 2020 » Gradient based sample selection for online continual learning
• April 09, 2019 » Towards a natural benchmark for continual learning
• March 12, 2019 » Model Primitive Hierarchical Lifelong Reinforcement Learning
• January 08, 2019 » Efficient Lifelong Learning with A-GEM
• March 05, 2018 » An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks

Causal Learning

• March 12, 2020 » Competitive Training of Mixtures of Independent Deep Generative Models
• July 11, 2018 » Learning Independent Causal Mechanisms

Causality

• March 12, 2020 » Competitive Training of Mixtures of Independent Deep Generative Models
• July 11, 2018 » Learning Independent Causal Mechanisms

Chemistry

• April 08, 2018 » Neural Message Passing for Quantum Chemistry

Classifier

• August 24, 2020 » Alpha Net--Adaptation with Composition in Classifier Space

Click-Through Rate

• March 08, 2021 » Practical Lessons from Predicting Clicks on Ads at Facebook
• March 01, 2021 » Ad Click Prediction - a View from the Trenches

Clustering

• March 12, 2020 » Competitive Training of Mixtures of Independent Deep Generative Models
• November 19, 2017 » Higher-order organization of complex networks

Compositionality

• March 29, 2021 » Synthesized Policies for Transfer and Adaptation across Tasks and Environments
• January 04, 2021 » Compositional Explanations of Neurons
• August 24, 2020 » Alpha Net--Adaptation with Composition in Classifier Space
• May 21, 2019 » Good-Enough Compositional Data Augmentation

Conditional Computation

• August 14, 2020 » Outrageously Large Neural Networks--The Sparsely-Gated Mixture-of-Experts Layer

Container

• December 21, 2020 » Design patterns for container-based distributed systems

Continual Learning

• February 22, 2021 » Anatomy of Catastrophic Forgetting - Hidden Representations and Task Semantics
• February 08, 2021 » Continual learning with hypernetworks
• January 18, 2021 » Energy-based Models for Continual Learning
• October 12, 2020 » Remembering for the Right Reasons - Explanations Reduce Catastrophic Forgetting
• February 13, 2020 » Gradient based sample selection for online continual learning
• January 02, 2020 » Superposition of many models into one
• April 09, 2019 » Towards a natural benchmark for continual learning
• March 12, 2019 » Model Primitive Hierarchical Lifelong Reinforcement Learning
• January 08, 2019 » Efficient Lifelong Learning with A-GEM
• July 04, 2018 » Memory-based Parameter Adaptation

Contrastive

• April 30, 2020 » Supervised Contrastive Learning
• April 09, 2020 » CURL - Contrastive Unsupervised Representations for Reinforcement Learning

Contrastive Learning

• April 30, 2020 » Supervised Contrastive Learning
• April 09, 2020 » CURL - Contrastive Unsupervised Representations for Reinforcement Learning

Conversational Agent

• January 22, 2018 » Emotional Chatting Machine - Emotional Conversation Generation with Internal and External Memory

Count Based VQA

• May 06, 2018 » Learning to Count Objects in Natural Images for Visual Question Answering

Credit Assignment

• July 09, 2020 » Decentralized Reinforcement Learning -- Global Decision-Making via Local Economic Transactions

Curriculum Learning

• February 15, 2021 » When Do Curricula Work?
• October 18, 2018 » BabyAI - First Steps Towards Grounded Language Learning With a Human In the Loop

DBMS

• December 14, 2020 » Cassandra - a decentralized structured storage system
• December 07, 2020 » CAP twelve years later - How the rules have changed
• November 30, 2020 » Consistency Tradeoffs in Modern Distributed Database System Design
• November 16, 2020 » Data Management for Internet-Scale Single-Sign-On

DRL

• November 02, 2020 » One Solution is Not All You Need - Few-Shot Extrapolation via Structured MaxEnt RL
• September 07, 2020 » Revisiting Fundamentals of Experience Replay
• August 31, 2020 » Deep Reinforcement Learning and the Deadly Triad
• July 02, 2020 » When to use parametric models in reinforcement learning?
• June 25, 2020 » Network Randomization - A Simple Technique for Generalization in Deep Reinforcement Learning
• April 09, 2020 » CURL - Contrastive Unsupervised Representations for Reinforcement Learning
• January 23, 2020 » Observational Overfitting in Reinforcement Learning
• December 05, 2019 » Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
• September 12, 2019 » Gossip based Actor-Learner Architectures for Deep RL
• August 08, 2019 » Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models
• August 01, 2019 » Assessing Generalization in Deep Reinforcement Learning
• July 25, 2019 » Quantifying Generalization in Reinforcement Learning

Data

• December 14, 2020 » Cassandra - a decentralized structured storage system
• November 30, 2020 » Consistency Tradeoffs in Modern Distributed Database System Design
• November 16, 2020 » Data Management for Internet-Scale Single-Sign-On

Data Augmentation

• February 27, 2020 » mixup - Beyond Empirical Risk Minimization
• May 21, 2019 » Good-Enough Compositional Data Augmentation

Data Mining

• March 08, 2021 » Practical Lessons from Predicting Clicks on Ads at Facebook
• March 01, 2021 » Ad Click Prediction - a View from the Trenches

Database

• December 14, 2020 » Cassandra - a decentralized structured storage system
• December 07, 2020 » CAP twelve years later - How the rules have changed
• November 30, 2020 » Consistency Tradeoffs in Modern Distributed Database System Design
• November 16, 2020 » Data Management for Internet-Scale Single-Sign-On

Dataset

• December 12, 2019 » Everything Happens for a Reason - Discovering the Purpose of Actions in Procedural Text
• August 29, 2019 » PHYRE - A New Benchmark for Physical Reasoning
• August 15, 2019 » Abductive Commonsense Reasoning
• January 14, 2018 » Exploring Models and Data for Image Question Answering
• October 15, 2017 » Reading Wikipedia to Answer Open-Domain Questions
• May 23, 2017 » Neural Module Networks
• May 14, 2017 » Making the V in VQA Matter - Elevating the Role of Image Understanding in Visual Question Answering
• April 27, 2017 » VQA-Visual Question Answering

Decentralized Reinforcement Learning

• July 09, 2020 » Decentralized Reinforcement Learning -- Global Decision-Making via Local Economic Transactions

Deep Reinforcement Learning

• November 02, 2020 » One Solution is Not All You Need - Few-Shot Extrapolation via Structured MaxEnt RL
• September 07, 2020 » Revisiting Fundamentals of Experience Replay
• August 31, 2020 » Deep Reinforcement Learning and the Deadly Triad
• July 02, 2020 » When to use parametric models in reinforcement learning?
• June 25, 2020 » Network Randomization - A Simple Technique for Generalization in Deep Reinforcement Learning
• April 09, 2020 » CURL - Contrastive Unsupervised Representations for Reinforcement Learning
• January 23, 2020 » Observational Overfitting in Reinforcement Learning
• December 05, 2019 » Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
• September 12, 2019 » Gossip based Actor-Learner Architectures for Deep RL
• August 08, 2019 » Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models
• August 01, 2019 » Assessing Generalization in Deep Reinforcement Learning
• July 25, 2019 » Quantifying Generalization in Reinforcement Learning
• June 01, 2019 » Relational Reinforcement Learning

Dependency Parsing

• June 03, 2017 » A Fast and Accurate Dependency Parser using Neural Networks

Design Pattern

• December 21, 2020 » Design patterns for container-based distributed systems

Distributed Computing

• January 11, 2021 » GPipe - Easy Scaling with Micro-Batch Pipeline Parallelism
• August 14, 2020 » Outrageously Large Neural Networks--The Sparsely-Gated Mixture-of-Experts Layer
• January 09, 2020 » Accurate, Large Minibatch SGD - Training ImageNet in 1 Hour

Distributed Reinforcement Learning

• September 12, 2019 » Gossip based Actor-Learner Architectures for Deep RL

Distributed SGD

• January 09, 2020 » Accurate, Large Minibatch SGD - Training ImageNet in 1 Hour

Distributed Systems

• March 15, 2021 » The Tail at Scale
• December 21, 2020 » Design patterns for container-based distributed systems
• December 14, 2020 » Cassandra - a decentralized structured storage system
• December 07, 2020 » CAP twelve years later - How the rules have changed
• November 30, 2020 » Consistency Tradeoffs in Modern Distributed Database System Design
• November 16, 2020 » Data Management for Internet-Scale Single-Sign-On
• September 21, 2020 » Harvest, Yield, and Scalable Tolerant Systems

Dynamical System

• February 17, 2018 » Neural Relational Inference for Interacting Systems

EBM

• January 18, 2021 » Energy-based Models for Continual Learning
• February 06, 2020 » Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One

ECCV

• March 05, 2020 » What Does Classifying More Than 10,000 Image Categories Tell Us?

ECCV 2010

• March 05, 2020 » What Does Classifying More Than 10,000 Image Categories Tell Us?

EMNLP

• December 12, 2019 » Everything Happens for a Reason - Discovering the Purpose of Actions in Procedural Text
• March 11, 2018 » Improving Information Extraction by Acquiring External Evidence with Reinforcement Learning
• November 28, 2017 » Two-Stage Synthesis Networks for Transfer Learning in Machine Comprehension
• October 01, 2017 » Task-Oriented Query Reformulation with Reinforcement Learning
• June 17, 2017 » A Decomposable Attention Model for Natural Language Inference
• June 03, 2017 » A Fast and Accurate Dependency Parser using Neural Networks

EMNLP 2014

• June 03, 2017 » A Fast and Accurate Dependency Parser using Neural Networks

EMNLP 2016

• March 11, 2018 » Improving Information Extraction by Acquiring External Evidence with Reinforcement Learning
• June 17, 2017 » A Decomposable Attention Model for Natural Language Inference

EMNLP 2017

• November 28, 2017 » Two-Stage Synthesis Networks for Transfer Learning in Machine Comprehension
• October 01, 2017 » Task-Oriented Query Reformulation with Reinforcement Learning

EMNLP 2019

• December 12, 2019 » Everything Happens for a Reason - Discovering the Purpose of Actions in Procedural Text

ERM

• February 27, 2020 » mixup - Beyond Empirical Risk Minimization

Economics

• July 09, 2020 » Decentralized Reinforcement Learning -- Global Decision-Making via Local Economic Transactions

Embedding

• March 26, 2019 » GNN Explainer - A Tool for Post-hoc Explanation of Graph Neural Networks
• February 19, 2019 » TuckER - Tensor Factorization for Knowledge Graph Completion
• December 11, 2018 » Representation Tradeoffs for Hyperbolic Embeddings
• October 11, 2018 » Poincaré Embeddings for Learning Hierarchical Representations
• April 02, 2018 » Unsupervised Learning by Predicting Noise
• January 29, 2018 » StarSpace - Embed All The Things!
• December 24, 2017 » PTE - Predictive Text Embedding through Large-scale Heterogeneous Text Networks
• December 11, 2017 » Revisiting Semi-Supervised Learning with Graph Embeddings
• October 28, 2017 » HARP - Hierarchical Representation Learning for Networks
• August 21, 2017 » Learning to Compute Word Embeddings On the Fly
• June 26, 2017 » Two/Too Simple Adaptations of Word2Vec for Syntax Problems
• May 07, 2017 » Conditional Similarity Networks

Emergent Language

• September 12, 2018 » Emergence of Grounded Compositional Language in Multi-Agent Populations

Empirical

• February 15, 2021 » When Do Curricula Work?
• September 07, 2020 » Revisiting Fundamentals of Experience Replay
• August 31, 2020 » Deep Reinforcement Learning and the Deadly Triad
• June 18, 2020 » On the Difficulty of Warm-Starting Neural Network Training

Empirical Advice

• March 08, 2021 » Practical Lessons from Predicting Clicks on Ads at Facebook
• March 01, 2021 » Ad Click Prediction - a View from the Trenches
• August 31, 2020 » Deep Reinforcement Learning and the Deadly Triad
• January 09, 2020 » Accurate, Large Minibatch SGD - Training ImageNet in 1 Hour
• September 05, 2019 » How to train your MAML
• March 16, 2019 » To Tune or Not to Tune? Adapting Pretrained Representations to Diverse Tasks

Energy-Based Models

• January 18, 2021 » Energy-based Models for Continual Learning
• February 06, 2020 » Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One

Engineering

• March 22, 2021 » Deep Neural Networks for YouTube Recommendations
• March 15, 2021 » The Tail at Scale
• March 08, 2021 » Practical Lessons from Predicting Clicks on Ads at Facebook
• March 01, 2021 » Ad Click Prediction - a View from the Trenches
• January 11, 2021 » GPipe - Easy Scaling with Micro-Batch Pipeline Parallelism
• December 21, 2020 » Design patterns for container-based distributed systems
• December 14, 2020 » Cassandra - a decentralized structured storage system
• December 07, 2020 » CAP twelve years later - How the rules have changed
• November 30, 2020 » Consistency Tradeoffs in Modern Distributed Database System Design
• November 16, 2020 » Data Management for Internet-Scale Single-Sign-On
• November 09, 2020 » Searching for Build Debt - Experiences Managing Technical Debt at Google

Entropy

• January 29, 2019 » Diversity is All You Need - Learning Skills without a Reward Function

Environment

• July 25, 2019 » Quantifying Generalization in Reinforcement Learning
• October 18, 2018 » BabyAI - First Steps Towards Grounded Language Learning With a Human In the Loop

Evaluating Generalization

• January 23, 2020 » Observational Overfitting in Reinforcement Learning
• August 01, 2019 » Assessing Generalization in Deep Reinforcement Learning
• July 25, 2019 » Quantifying Generalization in Reinforcement Learning

Evaluation

• January 23, 2020 » Observational Overfitting in Reinforcement Learning
• August 01, 2019 » Assessing Generalization in Deep Reinforcement Learning
• July 25, 2019 » Quantifying Generalization in Reinforcement Learning

Explainability

• January 04, 2021 » Compositional Explanations of Neurons

Exploration

• June 08, 2019 » Meta-Reinforcement Learning of Structured Exploration Strategies

Factorization

• February 19, 2019 » TuckER - Tensor Factorization for Knowledge Graph Completion

Finetuning

• February 20, 2020 » ELECTRA - Pre-training Text Encoders as Discriminators Rather Than Generators

GNN

• November 28, 2019 » Contrastive Learning of Structured World Models
• March 26, 2019 » GNN Explainer - A Tool for Post-hoc Explanation of Graph Neural Networks
• January 02, 2019 » Pre-training Graph Neural Networks with Kernels
• August 16, 2018 » Hierarchical Graph Representation Learning with Differentiable Pooling
• February 24, 2018 » Learning an SAT Solver from Single-Bit Supervision
• February 17, 2018 » Neural Relational Inference for Interacting Systems

GPT

• February 10, 2023 » Toolformer - Language Models Can Teach Themselves to Use Tools

Gating

• August 14, 2020 » Outrageously Large Neural Networks--The Sparsely-Gated Mixture-of-Experts Layer

Generalizatio

• March 29, 2021 » Synthesized Policies for Transfer and Adaptation across Tasks and Environments

Generalization

• November 02, 2020 » One Solution is Not All You Need - Few-Shot Extrapolation via Structured MaxEnt RL
• July 16, 2020 » Averaging Weights leads to Wider Optima and Better Generalization
• June 25, 2020 » Network Randomization - A Simple Technique for Generalization in Deep Reinforcement Learning
• January 23, 2020 » Observational Overfitting in Reinforcement Learning
• August 01, 2019 » Assessing Generalization in Deep Reinforcement Learning
• July 25, 2019 » Quantifying Generalization in Reinforcement Learning

Generative Models

• March 12, 2020 » Competitive Training of Mixtures of Independent Deep Generative Models
• February 06, 2020 » Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One

Geometry

• September 28, 2020 » A Foliated View of Transfer Learning

Gradient Manipulation

• August 06, 2020 » Gradient Surgery for Multi-Task Learning
• July 30, 2020 » GradNorm--Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks

Gradient Normalization

• July 30, 2020 » GradNorm--Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks

Graph

• December 12, 2019 » Everything Happens for a Reason - Discovering the Purpose of Actions in Procedural Text
• November 28, 2019 » Contrastive Learning of Structured World Models
• March 26, 2019 » GNN Explainer - A Tool for Post-hoc Explanation of Graph Neural Networks
• February 19, 2019 » TuckER - Tensor Factorization for Knowledge Graph Completion
• January 02, 2019 » Pre-training Graph Neural Networks with Kernels
• December 11, 2018 » Representation Tradeoffs for Hyperbolic Embeddings
• October 11, 2018 » Poincaré Embeddings for Learning Hierarchical Representations
• August 16, 2018 » Hierarchical Graph Representation Learning with Differentiable Pooling
• April 08, 2018 » Neural Message Passing for Quantum Chemistry
• February 24, 2018 » Learning an SAT Solver from Single-Bit Supervision
• February 17, 2018 » Neural Relational Inference for Interacting Systems
• January 29, 2018 » StarSpace - Embed All The Things!
• December 24, 2017 » PTE - Predictive Text Embedding through Large-scale Heterogeneous Text Networks
• December 11, 2017 » Revisiting Semi-Supervised Learning with Graph Embeddings
• November 19, 2017 » Higher-order organization of complex networks
• November 12, 2017 » Network Motifs - Simple Building Blocks of Complex Networks
• October 28, 2017 » HARP - Hierarchical Representation Learning for Networks

Graph Neural Network

• November 28, 2019 » Contrastive Learning of Structured World Models
• March 26, 2019 » GNN Explainer - A Tool for Post-hoc Explanation of Graph Neural Networks
• January 02, 2019 » Pre-training Graph Neural Networks with Kernels
• August 16, 2018 » Hierarchical Graph Representation Learning with Differentiable Pooling
• February 24, 2018 » Learning an SAT Solver from Single-Bit Supervision

Graph Representation

• March 26, 2019 » GNN Explainer - A Tool for Post-hoc Explanation of Graph Neural Networks
• February 19, 2019 » TuckER - Tensor Factorization for Knowledge Graph Completion
• January 02, 2019 » Pre-training Graph Neural Networks with Kernels
• December 11, 2018 » Representation Tradeoffs for Hyperbolic Embeddings
• October 11, 2018 » Poincaré Embeddings for Learning Hierarchical Representations
• August 16, 2018 » Hierarchical Graph Representation Learning with Differentiable Pooling
• April 08, 2018 » Neural Message Passing for Quantum Chemistry
• February 17, 2018 » Neural Relational Inference for Interacting Systems
• January 29, 2018 » StarSpace - Embed All The Things!
• December 11, 2017 » Revisiting Semi-Supervised Learning with Graph Embeddings
• October 28, 2017 » HARP - Hierarchical Representation Learning for Networks

Grounded Language Learning

• October 18, 2018 » BabyAI - First Steps Towards Grounded Language Learning With a Human In the Loop

HRL

• July 09, 2020 » Decentralized Reinforcement Learning -- Global Decision-Making via Local Economic Transactions
• March 12, 2019 » Model Primitive Hierarchical Lifelong Reinforcement Learning

Hierarchial RNN

• November 01, 2018 » Learned Optimizers that Scale and Generalize

Hierarchical RL

• January 15, 2019 » Hierarchical RL Using an Ensemble of Proprioceptive Periodic Policies

Hierarchical Reinforcement Learning

• July 09, 2020 » Decentralized Reinforcement Learning -- Global Decision-Making via Local Economic Transactions
• March 12, 2019 » Model Primitive Hierarchical Lifelong Reinforcement Learning

Hybrid Models

• February 06, 2020 » Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One

HyperNetwork

• February 08, 2021 » Continual learning with hypernetworks
• February 01, 2021 » Zero-shot Learning by Generating Task-specific Adapters
• January 25, 2021 » HyperNetworks

Hyperbolic Embedding

• December 11, 2018 » Representation Tradeoffs for Hyperbolic Embeddings
• October 11, 2018 » Poincaré Embeddings for Learning Hierarchical Representations

Hyperboloid Model

• December 11, 2018 » Representation Tradeoffs for Hyperbolic Embeddings

Hypothesis

• March 25, 2018 » The Lottery Ticket Hypothesis - Training Pruned Neural Networks

ICCV

• April 27, 2017 » VQA-Visual Question Answering

ICCV 2015

• April 27, 2017 » VQA-Visual Question Answering

ICLR

• February 22, 2021 » Anatomy of Catastrophic Forgetting - Hidden Representations and Task Semantics
• February 15, 2021 » When Do Curricula Work?
• February 08, 2021 » Continual learning with hypernetworks
• January 25, 2021 » HyperNetworks
• August 14, 2020 » Outrageously Large Neural Networks--The Sparsely-Gated Mixture-of-Experts Layer
• June 25, 2020 » Network Randomization - A Simple Technique for Generalization in Deep Reinforcement Learning
• February 27, 2020 » mixup - Beyond Empirical Risk Minimization
• February 20, 2020 » ELECTRA - Pre-training Text Encoders as Discriminators Rather Than Generators
• February 06, 2020 » Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One
• January 23, 2020 » Observational Overfitting in Reinforcement Learning
• January 16, 2020 » Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML
• December 19, 2019 » ALBERT - A Lite BERT for Self-supervised Learning of Language Representations
• September 05, 2019 » How to train your MAML
• June 27, 2019 » Measuring abstract reasoning in neural networks
• June 01, 2019 » Relational Reinforcement Learning
• April 02, 2019 » Meta-Learning Update Rules for Unsupervised Representation Learning
• January 29, 2019 » Diversity is All You Need - Learning Skills without a Reward Function
• January 15, 2019 » Hierarchical RL Using an Ensemble of Proprioceptive Periodic Policies
• January 08, 2019 » Efficient Lifelong Learning with A-GEM
• December 25, 2018 » Smooth Loss Functions for Deep Top-k Classification
• October 18, 2018 » BabyAI - First Steps Towards Grounded Language Learning With a Human In the Loop
• July 04, 2018 » Memory-based Parameter Adaptation
• May 06, 2018 » Learning to Count Objects in Natural Images for Visual Question Answering
• March 05, 2018 » An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks
• November 05, 2017 » Word Representations via Gaussian Embedding

ICLR 2014

• March 05, 2018 » An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks

ICLR 2015

• November 05, 2017 » Word Representations via Gaussian Embedding

ICLR 2016

• May 21, 2018 » Net2Net-Accelerating Learning via Knowledge Transfer

ICLR 2017

• January 25, 2021 » HyperNetworks
• August 14, 2020 » Outrageously Large Neural Networks--The Sparsely-Gated Mixture-of-Experts Layer

ICLR 2018

• December 25, 2018 » Smooth Loss Functions for Deep Top-k Classification
• October 18, 2018 » BabyAI - First Steps Towards Grounded Language Learning With a Human In the Loop
• July 04, 2018 » Memory-based Parameter Adaptation
• May 06, 2018 » Learning to Count Objects in Natural Images for Visual Question Answering

ICLR 2018'

• February 27, 2020 » mixup - Beyond Empirical Risk Minimization

ICLR 2019

• December 19, 2019 » ALBERT - A Lite BERT for Self-supervised Learning of Language Representations
• September 05, 2019 » How to train your MAML
• June 27, 2019 » Measuring abstract reasoning in neural networks
• June 01, 2019 » Relational Reinforcement Learning
• April 02, 2019 » Meta-Learning Update Rules for Unsupervised Representation Learning
• January 29, 2019 » Diversity is All You Need - Learning Skills without a Reward Function
• January 15, 2019 » Hierarchical RL Using an Ensemble of Proprioceptive Periodic Policies
• January 08, 2019 » Efficient Lifelong Learning with A-GEM

ICLR 2020

• February 08, 2021 » Continual learning with hypernetworks
• June 25, 2020 » Network Randomization - A Simple Technique for Generalization in Deep Reinforcement Learning
• February 20, 2020 » ELECTRA - Pre-training Text Encoders as Discriminators Rather Than Generators
• February 06, 2020 » Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One
• January 23, 2020 » Observational Overfitting in Reinforcement Learning
• January 16, 2020 » Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML

ICLR 2021

• February 22, 2021 » Anatomy of Catastrophic Forgetting - Hidden Representations and Task Semantics
• February 15, 2021 » When Do Curricula Work?

ICML

• September 07, 2020 » Revisiting Fundamentals of Experience Replay
• July 30, 2020 » GradNorm--Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks
• July 23, 2020 » TaskNorm--Rethinking Batch Normalization for Meta-Learning
• July 09, 2020 » Decentralized Reinforcement Learning -- Global Decision-Making via Local Economic Transactions
• July 25, 2019 » Quantifying Generalization in Reinforcement Learning
• July 18, 2019 » Set Transformer - A Framework for Attention-based Permutation-Invariant Neural Networks
• June 13, 2019 » Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations
• November 01, 2018 » Learned Optimizers that Scale and Generalize
• August 21, 2018 » A Semantic Loss Function for Deep Learning with Symbolic Knowledge
• July 19, 2018 » Kronecker Recurrent Units
• July 11, 2018 » Learning Independent Causal Mechanisms
• June 09, 2018 » Born Again Neural Networks
• December 11, 2017 » Revisiting Semi-Supervised Learning with Graph Embeddings

ICML 2016

• December 11, 2017 » Revisiting Semi-Supervised Learning with Graph Embeddings

ICML 2017

• November 01, 2018 » Learned Optimizers that Scale and Generalize

ICML 2018

• July 30, 2020 » GradNorm--Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks
• December 11, 2018 » Representation Tradeoffs for Hyperbolic Embeddings
• August 21, 2018 » A Semantic Loss Function for Deep Learning with Symbolic Knowledge
• July 19, 2018 » Kronecker Recurrent Units
• July 11, 2018 » Learning Independent Causal Mechanisms
• June 09, 2018 » Born Again Neural Networks

ICML 2019

• July 25, 2019 » Quantifying Generalization in Reinforcement Learning
• July 18, 2019 » Set Transformer - A Framework for Attention-based Permutation-Invariant Neural Networks
• June 13, 2019 » Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations

ICML 2020

• September 07, 2020 » Revisiting Fundamentals of Experience Replay
• July 09, 2020 » Decentralized Reinforcement Learning -- Global Decision-Making via Local Economic Transactions

ICML 2020'

• July 23, 2020 » TaskNorm--Rethinking Batch Normalization for Meta-Learning

IEEE

• December 07, 2020 » CAP twelve years later - How the rules have changed
• November 30, 2020 » Consistency Tradeoffs in Modern Distributed Database System Design
• November 09, 2020 » Searching for Build Debt - Experiences Managing Technical Debt at Google

IRL

• March 29, 2021 » Synthesized Policies for Transfer and Adaptation across Tasks and Environments
• June 13, 2019 » Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations

ImageNet

• November 23, 2020 » Exploring Simple Siamese Representation Learning
• April 30, 2020 » Supervised Contrastive Learning
• March 05, 2020 » What Does Classifying More Than 10,000 Image Categories Tell Us?
• January 09, 2020 » Accurate, Large Minibatch SGD - Training ImageNet in 1 Hour

Incremental Learning

• June 18, 2020 » On the Difficulty of Warm-Starting Neural Network Training
• July 04, 2018 » Memory-based Parameter Adaptation

Information Retrieval

• March 11, 2018 » Improving Information Extraction by Acquiring External Evidence with Reinforcement Learning
• October 01, 2017 » Task-Oriented Query Reformulation with Reinforcement Learning

Information Theory

• January 29, 2019 » Diversity is All You Need - Learning Skills without a Reward Function

Initialization

• March 25, 2018 » The Lottery Ticket Hypothesis - Training Pruned Neural Networks

Interactive Teaching

• October 18, 2018 » BabyAI - First Steps Towards Grounded Language Learning With a Human In the Loop

Interpretability

• January 04, 2021 » Compositional Explanations of Neurons

Invariance

• October 19, 2020 » Learning Explanations That Are Hard To Vary

Inverse Reinforcement Learning

• March 29, 2021 » Synthesized Policies for Transfer and Adaptation across Tasks and Environments
• June 13, 2019 » Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations

KD

• June 09, 2018 » Born Again Neural Networks

KDD

• March 08, 2021 » Practical Lessons from Predicting Clicks on Ads at Facebook
• March 01, 2021 » Ad Click Prediction - a View from the Trenches
• December 24, 2017 » PTE - Predictive Text Embedding through Large-scale Heterogeneous Text Networks
• July 24, 2017 » ReasoNet - Learning to Stop Reading in Machine Comprehension

KDD 2013

• March 01, 2021 » Ad Click Prediction - a View from the Trenches

KDD 2014

• March 08, 2021 » Practical Lessons from Predicting Clicks on Ads at Facebook

KDD 2015

• December 24, 2017 » PTE - Predictive Text Embedding through Large-scale Heterogeneous Text Networks

KDD 2017

• July 24, 2017 » ReasoNet - Learning to Stop Reading in Machine Comprehension

KRU

• July 19, 2018 » Kronecker Recurrent Units

Kernel

• January 02, 2019 » Pre-training Graph Neural Networks with Kernels

Key Value

• November 16, 2020 » Data Management for Internet-Scale Single-Sign-On
• August 22, 2019 » Large Memory Layers with Product Keys

Knowledge Distillation

• June 09, 2018 » Born Again Neural Networks

Knowledge Transfer

• June 09, 2018 » Born Again Neural Networks
• May 21, 2018 » Net2Net-Accelerating Learning via Knowledge Transfer

Kronecker

• July 19, 2018 » Kronecker Recurrent Units

LL

• February 22, 2021 » Anatomy of Catastrophic Forgetting - Hidden Representations and Task Semantics
• February 08, 2021 » Continual learning with hypernetworks
• January 18, 2021 » Energy-based Models for Continual Learning
• October 12, 2020 » Remembering for the Right Reasons - Explanations Reduce Catastrophic Forgetting
• February 13, 2020 » Gradient based sample selection for online continual learning
• January 02, 2020 » Superposition of many models into one

LLM

• February 10, 2023 » Toolformer - Language Models Can Teach Themselves to Use Tools

LR

• March 18, 2018 » Cyclical Learning Rates for Training Neural Networks

Large Language Model

• February 10, 2023 » Toolformer - Language Models Can Teach Themselves to Use Tools

Latency

• March 22, 2021 » Deep Neural Networks for YouTube Recommendations
• March 15, 2021 » The Tail at Scale
• December 07, 2020 » CAP twelve years later - How the rules have changed
• November 30, 2020 » Consistency Tradeoffs in Modern Distributed Database System Design

Latent Variable

• November 02, 2020 » One Solution is Not All You Need - Few-Shot Extrapolation via Structured MaxEnt RL
• February 17, 2018 » Neural Relational Inference for Interacting Systems

Learning Optimizer'

• November 01, 2018 » Learned Optimizers that Scale and Generalize

Learning Rate

• March 18, 2018 » Cyclical Learning Rates for Training Neural Networks

Lifelong Learning

• February 22, 2021 » Anatomy of Catastrophic Forgetting - Hidden Representations and Task Semantics
• February 08, 2021 » Continual learning with hypernetworks
• January 18, 2021 » Energy-based Models for Continual Learning
• October 12, 2020 » Remembering for the Right Reasons - Explanations Reduce Catastrophic Forgetting
• February 13, 2020 » Gradient based sample selection for online continual learning
• January 02, 2020 » Superposition of many models into one
• April 09, 2019 » Towards a natural benchmark for continual learning
• March 12, 2019 » Model Primitive Hierarchical Lifelong Reinforcement Learning
• January 08, 2019 » Efficient Lifelong Learning with A-GEM
• May 21, 2018 » Net2Net-Accelerating Learning via Knowledge Transfer

Linear Algebra

• February 19, 2019 » TuckER - Tensor Factorization for Knowledge Graph Completion

Linear Model

• February 19, 2019 » TuckER - Tensor Factorization for Knowledge Graph Completion

Long-tailed Dataset

• August 24, 2020 » Alpha Net--Adaptation with Composition in Classifier Space

Loss

• December 25, 2018 » Smooth Loss Functions for Deep Top-k Classification
• August 21, 2018 » A Semantic Loss Function for Deep Learning with Symbolic Knowledge

Loss Function

• December 25, 2018 » Smooth Loss Functions for Deep Top-k Classification
• August 21, 2018 » A Semantic Loss Function for Deep Learning with Symbolic Knowledge

MAML

• July 23, 2020 » TaskNorm--Rethinking Batch Normalization for Meta-Learning
• January 16, 2020 » Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML
• September 05, 2019 » How to train your MAML

MANN

• October 25, 2018 » One-shot Learning with Memory-Augmented Neural Networks

MDP

• January 23, 2020 » Observational Overfitting in Reinforcement Learning
• December 26, 2019 » Towards a Unified Theory of State Abstraction for MDPs

ML

• March 22, 2021 » Deep Neural Networks for YouTube Recommendations
• March 08, 2021 » Practical Lessons from Predicting Clicks on Ads at Facebook
• March 01, 2021 » Ad Click Prediction - a View from the Trenches

MPNN

• April 08, 2018 » Neural Message Passing for Quantum Chemistry

Machine Comprehension

• November 28, 2017 » Two-Stage Synthesis Networks for Transfer Learning in Machine Comprehension
• October 15, 2017 » Reading Wikipedia to Answer Open-Domain Questions
• August 07, 2017 » R-NET - Machine Reading Comprehension with Self-matching Networks
• July 24, 2017 » ReasoNet - Learning to Stop Reading in Machine Comprehension

Machine Learning

• March 22, 2021 » Deep Neural Networks for YouTube Recommendations
• March 08, 2021 » Practical Lessons from Predicting Clicks on Ads at Facebook
• March 01, 2021 » Ad Click Prediction - a View from the Trenches

Markov Decision Process

• January 23, 2020 » Observational Overfitting in Reinforcement Learning
• December 26, 2019 » Towards a Unified Theory of State Abstraction for MDPs

Matrix

• February 19, 2019 » TuckER - Tensor Factorization for Knowledge Graph Completion

Matrix Factorization

• February 19, 2019 » TuckER - Tensor Factorization for Knowledge Graph Completion

Memory

• August 22, 2019 » Large Memory Layers with Product Keys
• February 05, 2019 » Linguistic Knowledge as Memory for Recurrent Neural Networks
• October 25, 2018 » One-shot Learning with Memory-Augmented Neural Networks

Memory Augmented Neural Network

• October 25, 2018 » One-shot Learning with Memory-Augmented Neural Networks

Message Passing

• April 08, 2018 » Neural Message Passing for Quantum Chemistry

Meta Learning

• July 23, 2020 » TaskNorm--Rethinking Batch Normalization for Meta-Learning
• January 16, 2020 » Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML
• September 05, 2019 » How to train your MAML
• June 08, 2019 » Meta-Reinforcement Learning of Structured Exploration Strategies
• April 02, 2019 » Meta-Learning Update Rules for Unsupervised Representation Learning
• January 22, 2019 » Modular meta-learning
• November 01, 2018 » Learned Optimizers that Scale and Generalize
• October 25, 2018 » One-shot Learning with Memory-Augmented Neural Networks

Meta Reinforcement Learning

• June 08, 2019 » Meta-Reinforcement Learning of Structured Exploration Strategies

Mixture of Experts

• August 14, 2020 » Outrageously Large Neural Networks--The Sparsely-Gated Mixture-of-Experts Layer

Model Parallelism

• January 11, 2021 » GPipe - Easy Scaling with Micro-Batch Pipeline Parallelism

Model-Based

• July 02, 2020 » When to use parametric models in reinforcement learning?
• December 05, 2019 » Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
• August 08, 2019 » Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models
• May 14, 2019 » Multiple Model-Based Reinforcement Learning
• August 08, 2018 » Imagination-Augmented Agents for Deep Reinforcement Learning

Model-Free

• July 02, 2020 » When to use parametric models in reinforcement learning?
• December 05, 2019 » Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
• August 08, 2018 » Imagination-Augmented Agents for Deep Reinforcement Learning

Modular ML

• January 22, 2019 » Modular meta-learning

Modular Meta Learning

• January 22, 2019 » Modular meta-learning

Modular Network

• January 22, 2019 » Modular meta-learning

Module

• January 22, 2019 » Modular meta-learning

Motif

• November 19, 2017 » Higher-order organization of complex networks
• November 12, 2017 » Network Motifs - Simple Building Blocks of Complex Networks

Mujoco

• January 15, 2019 » Hierarchical RL Using an Ensemble of Proprioceptive Periodic Policies

Multi Domain

• January 30, 2020 » Massively Multilingual Neural Machine Translation in the Wild - Findings and Challenges

Multi Modal

• September 27, 2018 » HoME - a Household Multimodal Environment
• July 01, 2017 » One Model To Learn Them All

Multi Model

• July 01, 2017 » One Model To Learn Them All

Multi Task

• August 06, 2020 » Gradient Surgery for Multi-Task Learning
• July 30, 2020 » GradNorm--Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks
• January 30, 2020 » Massively Multilingual Neural Machine Translation in the Wild - Findings and Challenges
• March 16, 2019 » To Tune or Not to Tune? Adapting Pretrained Representations to Diverse Tasks
• January 29, 2018 » StarSpace - Embed All The Things!

Multi-Agent

• September 12, 2018 » Emergence of Grounded Compositional Language in Multi-Agent Populations

NIPS

• December 18, 2018 » Hindsight Experience Replay
• September 27, 2018 » HoME - a Household Multimodal Environment
• August 08, 2018 » Imagination-Augmented Agents for Deep Reinforcement Learning
• January 14, 2018 » Exploring Models and Data for Image Question Answering
• January 06, 2018 » How transferable are features in deep neural networks
• December 31, 2017 » Distilling the Knowledge in a Neural Network
• August 27, 2017 » Pointer Networks

NIPS 2014

• January 06, 2018 » How transferable are features in deep neural networks
• December 31, 2017 » Distilling the Knowledge in a Neural Network

NIPS 2015

• January 14, 2018 » Exploring Models and Data for Image Question Answering
• August 27, 2017 » Pointer Networks

NIPS 2017

• December 18, 2018 » Hindsight Experience Replay
• September 27, 2018 » HoME - a Household Multimodal Environment
• August 08, 2018 » Imagination-Augmented Agents for Deep Reinforcement Learning

NIPS Workskop

• September 27, 2018 » HoME - a Household Multimodal Environment

NLG

• February 11, 2018 » Stylistic Transfer in Natural Language Generation Systems Using Recurrent Neural Networks

NLI

• January 04, 2021 » Compositional Explanations of Neurons
• August 15, 2019 » Abductive Commonsense Reasoning

NLP

• February 01, 2021 » Zero-shot Learning by Generating Task-specific Adapters
• February 20, 2020 » ELECTRA - Pre-training Text Encoders as Discriminators Rather Than Generators
• January 30, 2020 » Massively Multilingual Neural Machine Translation in the Wild - Findings and Challenges
• December 19, 2019 » ALBERT - A Lite BERT for Self-supervised Learning of Language Representations
• December 12, 2019 » Everything Happens for a Reason - Discovering the Purpose of Actions in Procedural Text
• August 22, 2019 » Large Memory Layers with Product Keys
• August 15, 2019 » Abductive Commonsense Reasoning
• May 21, 2019 » Good-Enough Compositional Data Augmentation
• March 16, 2019 » To Tune or Not to Tune? Adapting Pretrained Representations to Diverse Tasks
• February 05, 2019 » Linguistic Knowledge as Memory for Recurrent Neural Networks
• October 18, 2018 » BabyAI - First Steps Towards Grounded Language Learning With a Human In the Loop
• October 11, 2018 » Poincaré Embeddings for Learning Hierarchical Representations
• October 04, 2018 » When Recurrent Models Don’t Need To Be Recurrent
• September 12, 2018 » Emergence of Grounded Compositional Language in Multi-Agent Populations
• July 19, 2018 » Kronecker Recurrent Units
• May 06, 2018 » Learning to Count Objects in Natural Images for Visual Question Answering
• March 11, 2018 » Improving Information Extraction by Acquiring External Evidence with Reinforcement Learning
• February 11, 2018 » Stylistic Transfer in Natural Language Generation Systems Using Recurrent Neural Networks
• February 05, 2018 » Get To The Point - Summarization with Pointer-Generator Networks
• January 29, 2018 » StarSpace - Embed All The Things!
• January 22, 2018 » Emotional Chatting Machine - Emotional Conversation Generation with Internal and External Memory
• January 14, 2018 » Exploring Models and Data for Image Question Answering
• December 24, 2017 » PTE - Predictive Text Embedding through Large-scale Heterogeneous Text Networks
• November 28, 2017 » Two-Stage Synthesis Networks for Transfer Learning in Machine Comprehension
• November 05, 2017 » Word Representations via Gaussian Embedding
• October 15, 2017 » Reading Wikipedia to Answer Open-Domain Questions
• October 01, 2017 » Task-Oriented Query Reformulation with Reinforcement Learning
• September 22, 2017 » Refining Source Representations with Relation Networks for Neural Machine Translation
• August 27, 2017 » Pointer Networks
• August 21, 2017 » Learning to Compute Word Embeddings On the Fly
• August 07, 2017 » R-NET - Machine Reading Comprehension with Self-matching Networks
• July 24, 2017 » ReasoNet - Learning to Stop Reading in Machine Comprehension
• July 09, 2017 » Ask Me Anything - Dynamic Memory Networks for Natural Language Processing
• July 01, 2017 » One Model To Learn Them All
• June 26, 2017 » Two/Too Simple Adaptations of Word2Vec for Syntax Problems
• June 17, 2017 » A Decomposable Attention Model for Natural Language Inference
• June 03, 2017 » A Fast and Accurate Dependency Parser using Neural Networks
• May 23, 2017 » Neural Module Networks
• May 14, 2017 » Making the V in VQA Matter - Elevating the Role of Image Understanding in Visual Question Answering
• April 28, 2017 » Simple Baseline for Visual Question Answering
• April 27, 2017 » VQA-Visual Question Answering

NMT

• January 30, 2020 » Massively Multilingual Neural Machine Translation in the Wild - Findings and Challenges
• September 22, 2017 » Refining Source Representations with Relation Networks for Neural Machine Translation

Natural Language Inference

• January 04, 2021 » Compositional Explanations of Neurons
• August 15, 2019 » Abductive Commonsense Reasoning
• June 17, 2017 » A Decomposable Attention Model for Natural Language Inference

Natural Language Processing

• February 01, 2021 » Zero-shot Learning by Generating Task-specific Adapters
• February 20, 2020 » ELECTRA - Pre-training Text Encoders as Discriminators Rather Than Generators
• January 30, 2020 » Massively Multilingual Neural Machine Translation in the Wild - Findings and Challenges
• December 19, 2019 » ALBERT - A Lite BERT for Self-supervised Learning of Language Representations
• August 22, 2019 » Large Memory Layers with Product Keys
• August 15, 2019 » Abductive Commonsense Reasoning
• March 16, 2019 » To Tune or Not to Tune? Adapting Pretrained Representations to Diverse Tasks
• February 05, 2019 » Linguistic Knowledge as Memory for Recurrent Neural Networks
• October 18, 2018 » BabyAI - First Steps Towards Grounded Language Learning With a Human In the Loop
• October 11, 2018 » Poincaré Embeddings for Learning Hierarchical Representations
• October 04, 2018 » When Recurrent Models Don’t Need To Be Recurrent
• September 12, 2018 » Emergence of Grounded Compositional Language in Multi-Agent Populations

Network

• December 24, 2017 » PTE - Predictive Text Embedding through Large-scale Heterogeneous Text Networks
• November 19, 2017 » Higher-order organization of complex networks
• November 12, 2017 » Network Motifs - Simple Building Blocks of Complex Networks

Network Embedding

• December 24, 2017 » PTE - Predictive Text Embedding through Large-scale Heterogeneous Text Networks

NeurIPS

• March 29, 2021 » Synthesized Policies for Transfer and Adaptation across Tasks and Environments
• January 11, 2021 » GPipe - Easy Scaling with Micro-Batch Pipeline Parallelism
• January 04, 2021 » Compositional Explanations of Neurons
• November 02, 2020 » One Solution is Not All You Need - Few-Shot Extrapolation via Structured MaxEnt RL
• February 13, 2020 » Gradient based sample selection for online continual learning
• June 08, 2019 » Meta-Reinforcement Learning of Structured Exploration Strategies

NeurIPS 2018

• March 29, 2021 » Synthesized Policies for Transfer and Adaptation across Tasks and Environments
• June 08, 2019 » Meta-Reinforcement Learning of Structured Exploration Strategies
• April 09, 2019 » Towards a natural benchmark for continual learning

NeurIPS 2019

• January 11, 2021 » GPipe - Easy Scaling with Micro-Batch Pipeline Parallelism
• February 13, 2020 » Gradient based sample selection for online continual learning

NeurIPS 2020

• January 04, 2021 » Compositional Explanations of Neurons
• November 02, 2020 » One Solution is Not All You Need - Few-Shot Extrapolation via Structured MaxEnt RL

NeurIPS Workshop 2018

• April 09, 2019 » Towards a natural benchmark for continual learning

Neural Computation

• May 14, 2019 » Multiple Model-Based Reinforcement Learning

Neural Computation 2002

• May 14, 2019 » Multiple Model-Based Reinforcement Learning

Neural Machine Translation

• January 30, 2020 » Massively Multilingual Neural Machine Translation in the Wild - Findings and Challenges

Neural Message Passing

• April 08, 2018 » Neural Message Passing for Quantum Chemistry

Neural Module Network

• May 23, 2017 » Neural Module Networks

Neurips

• July 02, 2020 » When to use parametric models in reinforcement learning?
• September 12, 2019 » Gossip based Actor-Learner Architectures for Deep RL
• August 08, 2019 » Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models

Neurips 2018

• August 08, 2019 » Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models

Neurips 2019

• July 02, 2020 » When to use parametric models in reinforcement learning?
• September 12, 2019 » Gossip based Actor-Learner Architectures for Deep RL

Normalization

• July 23, 2020 » TaskNorm--Rethinking Batch Normalization for Meta-Learning

OPT

• February 10, 2023 » Toolformer - Language Models Can Teach Themselves to Use Tools

OS

• September 21, 2020 » Harvest, Yield, and Scalable Tolerant Systems

Object-Oriented Learning

• September 14, 2020 » MONet - Unsupervised Scene Decomposition and Representation
• November 28, 2019 » Contrastive Learning of Structured World Models

Off policy RL

• September 07, 2020 » Revisiting Fundamentals of Experience Replay
• August 31, 2020 » Deep Reinforcement Learning and the Deadly Triad
• December 18, 2018 » Hindsight Experience Replay

One shot learning

• October 25, 2018 » One-shot Learning with Memory-Augmented Neural Networks

Online Learning

• June 18, 2020 » On the Difficulty of Warm-Starting Neural Network Training

Operating Systems

• September 21, 2020 » Harvest, Yield, and Scalable Tolerant Systems

Optimizer

• November 01, 2018 » Learned Optimizers that Scale and Generalize

Out of Distribution

• February 06, 2020 » Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One
• July 17, 2017 » Principled Detection of Out-of-Distribution Examples in Neural Networks

Out of Distribution Detection

• February 06, 2020 » Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One

Out of Vocabulary Words

• August 21, 2017 » Learning to Compute Word Embeddings On the Fly

Outlier Detection

• February 06, 2020 » Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One

POS

• July 09, 2017 » Ask Me Anything - Dynamic Memory Networks for Natural Language Processing

Physical Reasoning

• August 29, 2019 » PHYRE - A New Benchmark for Physical Reasoning

Physics

• August 29, 2019 » PHYRE - A New Benchmark for Physical Reasoning
• June 20, 2019 » Hamiltonian Neural Networks

Planning

• July 02, 2020 » When to use parametric models in reinforcement learning?
• December 05, 2019 » Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model

Poincare Ball Model

• December 11, 2018 » Representation Tradeoffs for Hyperbolic Embeddings
• October 11, 2018 » Poincaré Embeddings for Learning Hierarchical Representations

Pointer Network

• February 05, 2018 » Get To The Point - Summarization with Pointer-Generator Networks

Pooling

• August 16, 2018 » Hierarchical Graph Representation Learning with Differentiable Pooling

PreTrained Langauge Model

• February 10, 2023 » Toolformer - Language Models Can Teach Themselves to Use Tools

Pretraining

• February 20, 2020 » ELECTRA - Pre-training Text Encoders as Discriminators Rather Than Generators
• January 02, 2019 » Pre-training Graph Neural Networks with Kernels

Procedural Text

• December 12, 2019 » Everything Happens for a Reason - Discovering the Purpose of Actions in Procedural Text

Pruning Network

• March 25, 2018 » The Lottery Ticket Hypothesis - Training Pruned Neural Networks

QA

• March 16, 2019 » To Tune or Not to Tune? Adapting Pretrained Representations to Diverse Tasks
• February 05, 2019 » Linguistic Knowledge as Memory for Recurrent Neural Networks
• November 28, 2017 » Two-Stage Synthesis Networks for Transfer Learning in Machine Comprehension
• October 15, 2017 » Reading Wikipedia to Answer Open-Domain Questions
• August 07, 2017 » R-NET - Machine Reading Comprehension with Self-matching Networks
• July 24, 2017 » ReasoNet - Learning to Stop Reading in Machine Comprehension
• July 09, 2017 » Ask Me Anything - Dynamic Memory Networks for Natural Language Processing

RL

• March 29, 2021 » Synthesized Policies for Transfer and Adaptation across Tasks and Environments
• November 02, 2020 » One Solution is Not All You Need - Few-Shot Extrapolation via Structured MaxEnt RL
• September 07, 2020 » Revisiting Fundamentals of Experience Replay
• August 31, 2020 » Deep Reinforcement Learning and the Deadly Triad
• July 09, 2020 » Decentralized Reinforcement Learning -- Global Decision-Making via Local Economic Transactions
• July 02, 2020 » When to use parametric models in reinforcement learning?
• June 25, 2020 » Network Randomization - A Simple Technique for Generalization in Deep Reinforcement Learning
• April 09, 2020 » CURL - Contrastive Unsupervised Representations for Reinforcement Learning
• January 23, 2020 » Observational Overfitting in Reinforcement Learning
• December 26, 2019 » Towards a Unified Theory of State Abstraction for MDPs
• December 05, 2019 » Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
• September 12, 2019 » Gossip based Actor-Learner Architectures for Deep RL
• August 08, 2019 » Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models
• August 01, 2019 » Assessing Generalization in Deep Reinforcement Learning
• July 25, 2019 » Quantifying Generalization in Reinforcement Learning
• June 13, 2019 » Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations
• June 08, 2019 » Meta-Reinforcement Learning of Structured Exploration Strategies
• June 01, 2019 » Relational Reinforcement Learning
• May 14, 2019 » Multiple Model-Based Reinforcement Learning
• March 12, 2019 » Model Primitive Hierarchical Lifelong Reinforcement Learning
• January 29, 2019 » Diversity is All You Need - Learning Skills without a Reward Function
• January 15, 2019 » Hierarchical RL Using an Ensemble of Proprioceptive Periodic Policies
• December 18, 2018 » Hindsight Experience Replay
• October 18, 2018 » BabyAI - First Steps Towards Grounded Language Learning With a Human In the Loop
• August 08, 2018 » Imagination-Augmented Agents for Deep Reinforcement Learning
• March 11, 2018 » Improving Information Extraction by Acquiring External Evidence with Reinforcement Learning
• October 01, 2017 » Task-Oriented Query Reformulation with Reinforcement Learning
• August 07, 2017 » R-NET - Machine Reading Comprehension with Self-matching Networks
• July 24, 2017 » ReasoNet - Learning to Stop Reading in Machine Comprehension

RNN

• February 05, 2019 » Linguistic Knowledge as Memory for Recurrent Neural Networks
• November 01, 2018 » Learned Optimizers that Scale and Generalize
• October 04, 2018 » When Recurrent Models Don’t Need To Be Recurrent
• July 19, 2018 » Kronecker Recurrent Units

RRL

• June 01, 2019 » Relational Reinforcement Learning

Ranking

• March 22, 2021 » Deep Neural Networks for YouTube Recommendations

Reasoning

• December 12, 2019 » Everything Happens for a Reason - Discovering the Purpose of Actions in Procedural Text
• August 29, 2019 » PHYRE - A New Benchmark for Physical Reasoning
• August 15, 2019 » Abductive Commonsense Reasoning

Recommender

• March 22, 2021 » Deep Neural Networks for YouTube Recommendations

Recommender Systems

• March 22, 2021 » Deep Neural Networks for YouTube Recommendations

Recurrent Neural Network

• October 04, 2018 » When Recurrent Models Don’t Need To Be Recurrent
• July 19, 2018 » Kronecker Recurrent Units

Reinforcement Learning

• March 29, 2021 » Synthesized Policies for Transfer and Adaptation across Tasks and Environments
• November 02, 2020 » One Solution is Not All You Need - Few-Shot Extrapolation via Structured MaxEnt RL
• September 07, 2020 » Revisiting Fundamentals of Experience Replay
• August 31, 2020 » Deep Reinforcement Learning and the Deadly Triad
• July 09, 2020 » Decentralized Reinforcement Learning -- Global Decision-Making via Local Economic Transactions
• July 02, 2020 » When to use parametric models in reinforcement learning?
• June 25, 2020 » Network Randomization - A Simple Technique for Generalization in Deep Reinforcement Learning
• April 09, 2020 » CURL - Contrastive Unsupervised Representations for Reinforcement Learning
• January 23, 2020 » Observational Overfitting in Reinforcement Learning
• December 26, 2019 » Towards a Unified Theory of State Abstraction for MDPs
• December 05, 2019 » Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
• September 12, 2019 » Gossip based Actor-Learner Architectures for Deep RL
• August 08, 2019 » Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models
• August 01, 2019 » Assessing Generalization in Deep Reinforcement Learning
• July 25, 2019 » Quantifying Generalization in Reinforcement Learning
• June 13, 2019 » Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations
• June 08, 2019 » Meta-Reinforcement Learning of Structured Exploration Strategies
• June 01, 2019 » Relational Reinforcement Learning
• May 14, 2019 » Multiple Model-Based Reinforcement Learning
• March 12, 2019 » Model Primitive Hierarchical Lifelong Reinforcement Learning
• January 29, 2019 » Diversity is All You Need - Learning Skills without a Reward Function
• December 18, 2018 » Hindsight Experience Replay
• October 18, 2018 » BabyAI - First Steps Towards Grounded Language Learning With a Human In the Loop

Relation Learning

• December 12, 2019 » Everything Happens for a Reason - Discovering the Purpose of Actions in Procedural Text
• July 18, 2019 » Set Transformer - A Framework for Attention-based Permutation-Invariant Neural Networks
• June 27, 2019 » Measuring abstract reasoning in neural networks

Relational Inference

• February 17, 2018 » Neural Relational Inference for Interacting Systems

Relational Learning

• December 12, 2019 » Everything Happens for a Reason - Discovering the Purpose of Actions in Procedural Text
• November 28, 2019 » Contrastive Learning of Structured World Models
• July 18, 2019 » Set Transformer - A Framework for Attention-based Permutation-Invariant Neural Networks
• June 27, 2019 » Measuring abstract reasoning in neural networks
• June 01, 2019 » Relational Reinforcement Learning

Relational Network

• September 22, 2017 » Refining Source Representations with Relation Networks for Neural Machine Translation

Replay Buffer

• February 22, 2021 » Anatomy of Catastrophic Forgetting - Hidden Representations and Task Semantics
• January 18, 2021 » Energy-based Models for Continual Learning
• October 12, 2020 » Remembering for the Right Reasons - Explanations Reduce Catastrophic Forgetting
• September 07, 2020 » Revisiting Fundamentals of Experience Replay
• February 13, 2020 » Gradient based sample selection for online continual learning

Representation Analysis

• February 22, 2021 » Anatomy of Catastrophic Forgetting - Hidden Representations and Task Semantics

Representation Learning

• December 19, 2019 » ALBERT - A Lite BERT for Self-supervised Learning of Language Representations
• January 29, 2018 » StarSpace - Embed All The Things!
• November 05, 2017 » Word Representations via Gaussian Embedding
• September 22, 2017 » Refining Source Representations with Relation Networks for Neural Machine Translation

Robustness

• February 27, 2020 » mixup - Beyond Empirical Risk Minimization
• February 06, 2020 » Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One

SAT

• February 24, 2018 » Learning an SAT Solver from Single-Bit Supervision

SGD

• July 16, 2020 » Averaging Weights leads to Wider Optima and Better Generalization

SOTA

• December 19, 2019 » ALBERT - A Lite BERT for Self-supervised Learning of Language Representations
• May 06, 2018 » Learning to Count Objects in Natural Images for Visual Question Answering
• February 05, 2018 » Get To The Point - Summarization with Pointer-Generator Networks
• October 28, 2017 » HARP - Hierarchical Representation Learning for Networks
• October 22, 2017 » Swish - a Self-Gated Activation Function
• August 07, 2017 » R-NET - Machine Reading Comprehension with Self-matching Networks
• July 24, 2017 » ReasoNet - Learning to Stop Reading in Machine Comprehension
• July 09, 2017 » Ask Me Anything - Dynamic Memory Networks for Natural Language Processing
• June 17, 2017 » A Decomposable Attention Model for Natural Language Inference

SSL

• November 23, 2020 » Exploring Simple Siamese Representation Learning

SSO

• November 16, 2020 » Data Management for Internet-Scale Single-Sign-On

SWA

• July 16, 2020 » Averaging Weights leads to Wider Optima and Better Generalization

Sample Efficient

• April 09, 2020 » CURL - Contrastive Unsupervised Representations for Reinforcement Learning
• December 18, 2018 » Hindsight Experience Replay

Scale

• March 22, 2021 » Deep Neural Networks for YouTube Recommendations
• March 15, 2021 » The Tail at Scale
• March 08, 2021 » Practical Lessons from Predicting Clicks on Ads at Facebook
• March 01, 2021 » Ad Click Prediction - a View from the Trenches
• January 11, 2021 » GPipe - Easy Scaling with Micro-Batch Pipeline Parallelism
• December 21, 2020 » Design patterns for container-based distributed systems
• December 14, 2020 » Cassandra - a decentralized structured storage system
• December 07, 2020 » CAP twelve years later - How the rules have changed
• November 30, 2020 » Consistency Tradeoffs in Modern Distributed Database System Design
• November 16, 2020 » Data Management for Internet-Scale Single-Sign-On
• September 21, 2020 » Harvest, Yield, and Scalable Tolerant Systems
• January 30, 2020 » Massively Multilingual Neural Machine Translation in the Wild - Findings and Challenges

Science

• November 19, 2017 » Higher-order organization of complex networks
• November 12, 2017 » Network Motifs - Simple Building Blocks of Complex Networks

Science 2002

• November 12, 2017 » Network Motifs - Simple Building Blocks of Complex Networks

Science 2016

• November 19, 2017 » Higher-order organization of complex networks

Self Gated

• October 22, 2017 » Swish - a Self-Gated Activation Function

Self Supervised

• November 23, 2020 » Exploring Simple Siamese Representation Learning
• April 09, 2020 » CURL - Contrastive Unsupervised Representations for Reinforcement Learning

Semantic Loss

• August 21, 2018 » A Semantic Loss Function for Deep Learning with Symbolic Knowledge

Sentiment Analysis

• July 09, 2017 » Ask Me Anything - Dynamic Memory Networks for Natural Language Processing

Seq2Seq

• August 27, 2017 » Pointer Networks

Sequential models

• May 21, 2019 » Good-Enough Compositional Data Augmentation

Set

• July 18, 2019 » Set Transformer - A Framework for Attention-based Permutation-Invariant Neural Networks

Siamese

• November 23, 2020 » Exploring Simple Siamese Representation Learning

Softmax

• August 27, 2017 » Pointer Networks
• July 17, 2017 » Principled Detection of Out-of-Distribution Examples in Neural Networks

Software

• December 14, 2020 » Cassandra - a decentralized structured storage system
• November 30, 2020 » Consistency Tradeoffs in Modern Distributed Database System Design
• November 16, 2020 » Data Management for Internet-Scale Single-Sign-On
• November 09, 2020 » Searching for Build Debt - Experiences Managing Technical Debt at Google

Software Engineering

• December 21, 2020 » Design patterns for container-based distributed systems
• December 14, 2020 » Cassandra - a decentralized structured storage system
• November 30, 2020 » Consistency Tradeoffs in Modern Distributed Database System Design
• November 16, 2020 » Data Management for Internet-Scale Single-Sign-On
• November 09, 2020 » Searching for Build Debt - Experiences Managing Technical Debt at Google

Speech

• July 01, 2017 » One Model To Learn Them All

State Abstraction

• December 26, 2019 » Towards a Unified Theory of State Abstraction for MDPs

Stochastic Gradient Descent

• July 16, 2020 » Averaging Weights leads to Wider Optima and Better Generalization

Structured Exploration

• June 08, 2019 » Meta-Reinforcement Learning of Structured Exploration Strategies

Summarization

• February 05, 2018 » Get To The Point - Summarization with Pointer-Generator Networks

Symbolic Knowledge

• August 21, 2018 » A Semantic Loss Function for Deep Learning with Symbolic Knowledge

Synchronous SGD

• January 09, 2020 » Accurate, Large Minibatch SGD - Training ImageNet in 1 Hour

Systems

• March 22, 2021 » Deep Neural Networks for YouTube Recommendations
• March 15, 2021 » The Tail at Scale
• March 08, 2021 » Practical Lessons from Predicting Clicks on Ads at Facebook
• March 01, 2021 » Ad Click Prediction - a View from the Trenches
• January 11, 2021 » GPipe - Easy Scaling with Micro-Batch Pipeline Parallelism
• December 21, 2020 » Design patterns for container-based distributed systems
• December 14, 2020 » Cassandra - a decentralized structured storage system
• December 07, 2020 » CAP twelve years later - How the rules have changed
• November 30, 2020 » Consistency Tradeoffs in Modern Distributed Database System Design
• November 16, 2020 » Data Management for Internet-Scale Single-Sign-On
• November 09, 2020 » Searching for Build Debt - Experiences Managing Technical Debt at Google

Technical Debt

• November 09, 2020 » Searching for Build Debt - Experiences Managing Technical Debt at Google

Text-to-Text Transformer

• February 01, 2021 » Zero-shot Learning by Generating Task-specific Adapters

Theory

• September 28, 2020 » A Foliated View of Transfer Learning
• October 04, 2018 » When Recurrent Models Don’t Need To Be Recurrent

Transfer Learning

• March 29, 2021 » Synthesized Policies for Transfer and Adaptation across Tasks and Environments
• September 28, 2020 » A Foliated View of Transfer Learning
• August 24, 2020 » Alpha Net--Adaptation with Composition in Classifier Space
• June 18, 2020 » On the Difficulty of Warm-Starting Neural Network Training
• March 16, 2019 » To Tune or Not to Tune? Adapting Pretrained Representations to Diverse Tasks
• January 06, 2018 » How transferable are features in deep neural networks
• November 28, 2017 » Two-Stage Synthesis Networks for Transfer Learning in Machine Comprehension

Transformer

• February 01, 2021 » Zero-shot Learning by Generating Task-specific Adapters
• February 20, 2020 » ELECTRA - Pre-training Text Encoders as Discriminators Rather Than Generators
• December 19, 2019 » ALBERT - A Lite BERT for Self-supervised Learning of Language Representations

Tree

• October 11, 2018 » Poincaré Embeddings for Learning Hierarchical Representations

Tucker Decomposition

• February 19, 2019 » TuckER - Tensor Factorization for Knowledge Graph Completion

UAI

• July 16, 2020 » Averaging Weights leads to Wider Optima and Better Generalization

UAI 2018

• July 16, 2020 » Averaging Weights leads to Wider Optima and Better Generalization

USENIX

• December 21, 2020 » Design patterns for container-based distributed systems
• November 16, 2020 » Data Management for Internet-Scale Single-Sign-On

Unsupervised

• November 23, 2020 » Exploring Simple Siamese Representation Learning
• September 14, 2020 » MONet - Unsupervised Scene Decomposition and Representation
• April 09, 2020 » CURL - Contrastive Unsupervised Representations for Reinforcement Learning
• April 02, 2019 » Meta-Learning Update Rules for Unsupervised Representation Learning
• January 29, 2019 » Diversity is All You Need - Learning Skills without a Reward Function
• April 02, 2018 » Unsupervised Learning by Predicting Noise

VAE

• February 17, 2018 » Neural Relational Inference for Interacting Systems

VQA

• May 06, 2018 » Learning to Count Objects in Natural Images for Visual Question Answering
• January 14, 2018 » Exploring Models and Data for Image Question Answering
• May 23, 2017 » Neural Module Networks
• May 14, 2017 » Making the V in VQA Matter - Elevating the Role of Image Understanding in Visual Question Answering
• April 28, 2017 » Simple Baseline for Visual Question Answering
• April 27, 2017 » VQA-Visual Question Answering

Virtual Embodiment

• September 27, 2018 » HoME - a Household Multimodal Environment

WACV

• March 18, 2018 » Cyclical Learning Rates for Training Neural Networks

WACV 2017

• March 18, 2018 » Cyclical Learning Rates for Training Neural Networks

Weight Adaptation

• July 04, 2018 » Memory-based Parameter Adaptation

Word Vectors

• January 29, 2018 » StarSpace - Embed All The Things!
• November 05, 2017 » Word Representations via Gaussian Embedding
• June 26, 2017 » Two/Too Simple Adaptations of Word2Vec for Syntax Problems

Workshop

• April 09, 2019 » Towards a natural benchmark for continual learning
• February 11, 2018 » Stylistic Transfer in Natural Language Generation Systems Using Recurrent Neural Networks

Zero Shot Generalization

• February 01, 2021 » Zero-shot Learning by Generating Task-specific Adapters

Zero-Shot

• February 01, 2021 » Zero-shot Learning by Generating Task-specific Adapters