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
Imperceptible Black-box Attack via Refining in Salient Region
Implicit Bias of Adversarial Training for Deep Neural Networks
Implicit Bias of MSE Gradient Optimization in Underparameterized Neural Networks
Implicit Bias of Projected Subgradient Method Gives Provable Robust Recovery of Subspaces of Unknown Codimension
Implicit Jacobian regularization weighted with impurity of probability output
Implicit Regularization of Bregman Proximal Point Algorithm and Mirror Descent on Separable Data
ImpressLearn: Continual Learning via Combined Task Impressions
Improved deterministic l2 robustness on CIFAR-10 and CIFAR-100
Improved Image Generation via Sparsity
Improving Adversarial Defense with Self-supervised Test-time Fine-tuning
Improving and Assessing Anomaly Detectors for Large-Scale Settings
Improving Fairness via Federated Learning
Improving Federated Learning Face Recognition via Privacy-Agnostic Clusters
Improving Generative Flow Networks with Path Regularization
Improving greedy core-set configurations for active learning with uncertainty-scaled distances
Improving Hyperparameter Optimization by Planning Ahead
Improving Long-Horizon Imitation Through Language Prediction
Improving Meta-Continual Learning Representations with Representation Replay
Improving Mutual Information Estimation with Annealed and Energy-Based Bounds
Improving Neural Network Generalization via Promoting Within-Layer Diversity
Improving Non-Autoregressive Translation Models Without Distillation
Improving Out-of-Distribution Robustness via Selective Augmentation
Improving State-of-the-Art in One-Class Classification by Leveraging Unlabeled Data
Improving the Accuracy of Learning Example Weights for Imbalance Classification
In a Nutshell, the Human Asked for This: Latent Goals for Following Temporal Specifications
Increase and Conquer: Training Graph Neural Networks on Growing Graphs
Increasing the Cost of Model Extraction with Calibrated Proof of Work
Incremental False Negative Detection for Contrastive Learning
In defense of dual-encoders for neural ranking
Independent Component Alignment for Multi-task Learning
Independent SE(3)-Equivariant Models for End-to-End Rigid Protein Docking
Indiscriminate Poisoning Attacks Are Shortcuts
Inducing Reusable Skills From Demonstrations with Option-Controller Network
Inductive Biases and Variable Creation in Self-Attention Mechanisms
Inductive Lottery Ticket Learning for Graph Neural Networks
Inductive Relation Prediction Using Analogy Subgraph Embeddings
Inference-Time Personalized Federated Learning
Inferring Offensiveness In Images From Natural Language Supervision
InfinityGAN: Towards Infinite-Pixel Image Synthesis
Influence-Based Reinforcement Learning for Intrinsically-Motivated Agents
Information-Aware Time Series Meta-Contrastive Learning
Information Bottleneck: Exact Analysis of (Quantized) Neural Networks
Information Gain Propagation: a New Way to Graph Active Learning with Soft Labels
Information Prioritization through Empowerment in Visual Model-based RL
Information-Theoretic Generalization Bounds for Iterative Semi-Supervised Learning
Information-theoretic Online Memory Selection for Continual Learning
Input Dependent Sparse Gaussian Processes
InstaHide’s Sample Complexity When Mixing Two Private Images
Instance-Adaptive Video Compression: Improving Neural Codecs by Training on the Test Set
Interacting Contour Stochastic Gradient Langevin Dynamics

« prev Page 21/47 next »