ICLR 2022

2,337 papers

Top Research Directions

Research directions most represented by ICLR 2022 papers.

Bypassing the Computational Bottleneck of Adversarial Training 21
Sample Efficient Reinforcement Learning 19
The Mechanics of Benign Overfitting in High Dimensions 18
Clean Accuracy Degradation in Machine Learning Defenses 17
Overcoming the Homophily Assumption in Graph Neural Networks 13
Accelerating Sparse Neural Networks on Dense Hardware 13
Accelerating Neural Architecture Search Without Full Model Training 12
The Non-Linear Function Approximation Gap in Reinforcement Learning 12
The Mechanics of Backdoor Attacks in Neural Networks 12
Beyond the Lazy Training Regime of Neural Networks 11
The Infinite Width Approximation Gap in Deep Learning 10
Matrix-Free Curvature Estimation for Deep Learning 10
The Computational Overhead of Iterative Model Pruning 9
The Weisfeiler Lehman Expressivity Bottleneck 9
Why Theoretical FLOPs Fail to Predict Real Latency 9

Top Authors

AuthorPapers
Zhangyang Wang23
Sergey Levine21
Tianlong Chen15
Tongliang Liu14
Bo Han13
Chelsea Finn13
Gang Niu13
Jun Wang13
Yoshua Bengio13
Bernhard Schölkopf12
Joshua B. Tenenbaum12
J Zico Kolter12
Ping Li12
Tie-Yan Liu12
Dacheng Tao11
Stephan Günnemann11
Tom Goldstein11
Masashi Sugiyama10
Pieter Abbeel9
Pin-Yu Chen9

Impactful Papers

Papers from ICLR 2022 that shaped research clusters.

Foundational

Influential

Papers

Title
Learning Temporally-Consistent Representations for Data-Efficient Reinforcement Learning
Learning the Dynamics of Physical Systems from Sparse Observations with Finite Element Networks
Learning the Representation of Behavior Styles with Imitation Learning
Learning to Abstain in the Presence of Uninformative Data
Learning to Annotate Part Segmentation with Gradient Matching
Learning to Collaborate
Learning to Complete Code with Sketches
Learning-to-Count by Learning-to-Rank: Weakly Supervised Object Counting & Localization Using Only Pairwise Image Rankings
Learning to Dequantise with Truncated Flows
Learning to Downsample for Segmentation of Ultra-High Resolution Images
Learning to Efficiently Sample from Diffusion Probabilistic Models
Learning to Extend Molecular Scaffolds with Structural Motifs
Learning to Generalize across Domains on Single Test Samples
Learning to Generalize Compositionally by Transferring Across Semantic Parsing Tasks
Learning to Give Checkable Answers with Prover-Verifier Games
Learning to Guide and to be Guided in the Architect-Builder Problem
Learning to Infer the Structure of Network Games
Learning to Learn with Generative Models of Neural Network Checkpoints
Learning to Map for Active Semantic Goal Navigation
Learning to Persuade
Learning to Pool in Graph Neural Networks for Extrapolation
Learning to reason with relational abstractions
Learning to Remember Patterns: Pattern Matching Memory Networks for Traffic Forecasting
Learning to Schedule Learning rate with Graph Neural Networks
Learning to Shape Rewards using a Game of Two Partners
Learning to Solve an Order Fulfillment Problem in Milliseconds with Edge-Feature-Embedded Graph Attention
Learning to Solve Combinatorial Problems via Efficient Exploration
Learning Towards The Largest Margins
Learning transferable motor skills with hierarchical latent mixture policies
Learning Transferable Reward for Query Object Localization with Policy Adaptation
Learning Universal User Representations via Self-Supervised Lifelong Behaviors Modeling
Learning Value Functions from Undirected State-only Experience
Learning Versatile Neural Architectures by Propagating Network Codes
Learning Vision-Guided Quadrupedal Locomotion End-to-End with Cross-Modal Transformers
Learning Visual-Linguistic Adequacy, Fidelity, and Fluency for Novel Object Captioning
Learning Weakly-supervised Contrastive Representations
Learning When and What to Ask: a Hierarchical Reinforcement Learning Framework
Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotations
Learn Locally, Correct Globally: A Distributed Algorithm for Training Graph Neural Networks
Learn the Time to Learn: Replay Scheduling for Continual Learning
Less data is more: Selecting informative and diverse subsets with balancing constraints
Less is More: Dimension Reduction Finds On-Manifold Adversarial Examples in Hard-Label Attacks
Let Your Heart Speak in its Mother Tongue: Multilingual Captioning of Cardiac Signals
Leveraging Automated Unit Tests for Unsupervised Code Translation
Leveraging unlabeled data to predict out-of-distribution performance
LFPT5: A Unified Framework for Lifelong Few-shot Language Learning Based on Prompt Tuning of T5
Lifting Imbalanced Regression with Self-Supervised Learning
Lightweight Convolutional Neural Networks By Hypercomplex Parameterization
LIGS: Learnable Intrinsic-Reward Generation Selection for Multi-Agent Learning
Likelihood Training of Schrödinger Bridge using Forward-Backward SDEs Theory

« prev Page 25/47 next »