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
Clean Images are Hard to Reblur: Exploiting the Ill-Posed Inverse Task for Dynamic Scene Deblurring
CLEVA-Compass: A Continual Learning Evaluation Assessment Compass to Promote Research Transparency and Comparability
ClimateGAN: Raising Climate Change Awareness by Generating Images of Floods
CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP
Closed-form Sample Probing for Learning Generative Models in Zero-shot Learning
Closed-loop Control for Online Continual Learning
Closed-Loop Control of Additive Manufacturing via Reinforcement Learning
Closed-Loop Data Transcription to an LDR via Minimaxing Rate Reduction
ClsVC: Learning Speech Representations with two different classification tasks.
Cluster-based Feature Importance Learning for Electronic Health Record Time-series
Clustered Task-Aware Meta-Learning by Learning from Learning Paths
C-MinHash: Improving Minwise Hashing with Circulant Permutation
Coarformer: Transformer for large graph via graph coarsening
CoBERL: Contrastive BERT for Reinforcement Learning
Code Editing from Few Exemplars by Adaptive Multi-Extent Composition
CodeTrek: Flexible Modeling of Code using an Extensible Relational Representation
Cognitively Inspired Learning of Incremental Drifting Concepts
Coherence-based Label Propagation over Time Series for Accelerated Active Learning
COLA: Consistent Learning with Opponent-Learning Awareness
Cold Brew: Distilling Graph Node Representations with Incomplete or Missing Neighborhoods
Collaborate to Defend Against Adversarial Attacks
Collaboration of Experts: Achieving 80% Top-1 Accuracy on ImageNet with 100M FLOPs
Collapse by Conditioning: Training Class-conditional GANs with Limited Data
ColoristaNet for Photorealistic Video Style Transfer
Combining Differential Privacy and Byzantine Resilience in Distributed SGD
Combining Diverse Feature Priors
CommsVAE: Learning the brain's macroscale communication dynamics using coupled sequential VAEs
Communicate Then Adapt: An Effective Decentralized Adaptive Method for Deep Training
Communicating Natural Programs to Humans and Machines
Communicating via Markov Decision Processes
Communication-Efficient Actor-Critic Methods for Homogeneous Markov Games
Comparing Distributions by Measuring Differences that Affect Decision Making
ComPhy: Compositional Physical Reasoning of Objects and Events from Videos
Complete Verification via Multi-Neuron Relaxation Guided Branch-and-Bound
Complex Locomotion Skill Learning via Differentiable Physics
Complex-valued deep learning with differential privacy
Composing Features: Compositional Model Augmentation for Steerability of Music Transformers
Compositional Attention: Disentangling Search and Retrieval
Compositional Training for End-to-End Deep AUC Maximization
Compressed Predictive Information Coding
CoMPS: Continual Meta Policy Search
Concentric Spherical GNN for 3D Representation Learning
Concurrent Adversarial Learning for Large-Batch Training
Conditional Contrastive Learning with Kernel
Conditional Expectation based Value Decomposition for Scalable On-Demand Ride Pooling
Conditional GANs with Auxiliary Discriminative Classifier
Conditional Generative Quantile Networks via Optimal Transport and Convex Potentials
Conditional Image Generation by Conditioning Variational Auto-Encoders
Conditional Object-Centric Learning from Video
Conditional set generation using Seq2seq models

« prev Page 7/47 next »