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
Interactively Generating Explanations for Transformer Language Models
Interactive Model with Structural Loss for Language-based Abductive Reasoning
Interpretable Unsupervised Diversity Denoising and Artefact Removal
Interpreting Molecule Generative Models for Interactive Molecule Discovery
Interpreting Reinforcement Policies through Local Behaviors
Interrogating Paradigms in Self-supervised Graph Representation Learning
Intervention Adversarial Auto-Encoder
Interventional Black-Box Explanations
Intra-class Mixup for Out-of-Distribution Detection
Intriguing Properties of Input-dependent Randomized Smoothing
Intrusion-Free Graph Mixup
IntSGD: Adaptive Floatless Compression of Stochastic Gradients
Invariance-Guided Feature Evolution for Few-Shot Learning
Invariance in Policy Optimisation and Partial Identifiability in Reward Learning
Invariance Through Inference
Invariant Causal Mechanisms through Distribution Matching
Invariant Causal Representation Learning for Out-of-Distribution Generalization
Invariant Learning with Partial Group Labels
Inverse Online Learning: Understanding Non-Stationary and Reactionary Policies
I-PGD-AT: Efficient Adversarial Training via Imitating Iterative PGD Attack
Is Fairness Only Metric Deep? Evaluating and Addressing Subgroup Gaps in Deep Metric Learning
Is Heterophily A Real Nightmare For Graph Neural Networks on Performing Node Classification?
Is High Variance Unavoidable in RL? A Case Study in Continuous Control
Is Homophily a Necessity for Graph Neural Networks?
Is Importance Weighting Incompatible with Interpolating Classifiers?
Iterated Reasoning with Mutual Information in Cooperative and Byzantine Decentralized Teaming
Iterative Decoding for Compositional Generalization in Transformers
Iterative Hierarchical Attention for Answering Complex Questions over Long Documents
Iterative Memory Network for Long Sequential User Behavior Modeling in Recommender Systems
Iterative Refinement Graph Neural Network for Antibody Sequence-Structure Co-design
Iterative Sketching and its Application to Federated Learning
It Takes Four to Tango: Multiagent Self Play for Automatic Curriculum Generation
It Takes Two to Tango: Mixup for Deep Metric Learning
Joint Attention-Driven Domain Fusion and Noise-Tolerant Learning for Multi-Source Domain Adaptation
Joint Embedding Self-Supervised Learning in the Kernel Regime
Joint Shapley values: a measure of joint feature importance
Kalman Filter Is All You Need: Optimization Works When Noise Estimation Fails
Kernel Deformed Exponential Families for Sparse Continuous Attention
KINet: Keypoint Interaction Networks for Unsupervised Forward Modeling
KL Guided Domain Adaptation
KNIFE: Kernelized-Neural Differential Entropy Estimation
Knothe-Rosenblatt transport for Unsupervised Domain Adaptation
Knowledge Based Multilingual Language Model
Knowledge-Driven New Drug Recommendation
Knowledge-driven Scene Priors for Semantic Audio-Visual Embodied Navigation
Knowledge Guided Geometric Editing for Unsupervised Drug Design
Knowledge Infused Decoding
Knowledge Removal in Sampling-based Bayesian Inference
Know Thyself: Transferable Visual Control Policies Through Robot-Awareness
Know Your Action Set: Learning Action Relations for Reinforcement Learning

« prev Page 22/47 next »