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
Recycling Scraps: Improving Private Learning by Leveraging Intermediate Checkpoints
Red Alarm for Pre-trained Models: Universal Vulnerability to Neuron-Level Backdoor Attacks
Reducing Excessive Margin to Achieve a Better Accuracy vs. Robustness Trade-off
REFACTOR: Learning to Extract Theorems from Proofs
RegionViT: Regional-to-Local Attention for Vision Transformers
Regularized Autoencoders for Isometric Representation Learning
Regularized-OFU: an efficient algorithm for general contextual bandit with optimization oracles
Regularizing Deep Neural Networks with Stochastic Estimators of Hessian Trace
Reinforcement Learning for Adaptive Mesh Refinement
Reinforcement Learning in Presence of Discrete Markovian Context Evolution
Reinforcement Learning under a Multi-agent Predictive State Representation Model: Method and Theory
Reinforcement Learning with Efficient Active Feature Acquisition
Reinforcement Learning with Ex-Post Max-Min Fairness
Reinforcement Learning with Sparse Rewards using Guidance from Offline Demonstration
Relating transformers to models and neural representations of the hippocampal formation
Relational Learning with Variational Bayes
Relational Multi-Task Learning: Modeling Relations between Data and Tasks
Relational Surrogate Loss Learning
Relative Entropy Gradient Sampler for Unnormalized Distributions
Relative Molecule Self-Attention Transformer
RelaxLoss: Defending Membership Inference Attacks without Losing Utility
Reliable Adversarial Distillation with Unreliable Teachers
RelViT: Concept-guided Vision Transformer for Visual Relational Reasoning
Repairing Systematic Outliers by Learning Clean Subspaces in VAEs
Representation-Agnostic Shape Fields
Representational Continuity for Unsupervised Continual Learning
Representation Consolidation from Multiple Expert Teachers
Representation Disentanglement in Generative Models with Contrastive Learning
Representation Learning for Online and Offline RL in Low-rank MDPs
Representation mitosis in wide neural networks
Representations of Computer Programs in the Human Brain
Representing Mixtures of Word Embeddings with Mixtures of Topic Embeddings
ResGrad: Residual Denoising Diffusion Probabilistic Models for Text to Speech
Resilience to Multiple Attacks via Adversarially Trained MIMO Ensembles
Resmax: An Alternative Soft-Greedy Operator for Reinforcement Learning
Resolving label uncertainty with implicit generative models
Resolving Training Biases via Influence-based Data Relabeling
Resonance in Weight Space: Covariate Shift Can Drive Divergence of SGD with Momentum
Responsible Disclosure of Generative Models Using Scalable Fingerprinting
Restricted Category Removal from Model Representations using Limited Data
Rethinking Adversarial Transferability from a Data Distribution Perspective
Rethinking Again the Value of Network Pruning -- A Dynamical Isometry Perspective
Rethinking Backdoor Data Poisoning Attacks in the Context of Semi-Supervised Learning
Rethinking Class-Prior Estimation for Positive-Unlabeled Learning
Rethinking Goal-Conditioned Supervised Learning and Its Connection to Offline RL
Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework
Rethinking Supervised Pre-Training for Better Downstream Transferring
Rethinking the limiting dynamics of SGD: modified loss, phase space oscillations, and anomalous diffusion
Retrieval-Augmented Reinforcement Learning
Retriever: Learning Content-Style Representation as a Token-Level Bipartite Graph

« prev Page 36/47 next »