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
Token Pooling in Vision Transformers
ToM2C: Target-oriented Multi-agent Communication and Cooperation with Theory of Mind
Top-label calibration and multiclass-to-binary reductions
Top-N: Equivariant Set and Graph Generation without Exchangeability
Topological Experience Replay
Topological Graph Neural Networks
Topologically Regularized Data Embeddings
TorchGeo: deep learning with geospatial data
TotalRecall: A Bidirectional Candidates Generation Framework for Large Scale Recommender \& Advertising Systems
Toward Efficient Low-Precision Training: Data Format Optimization and Hysteresis Quantization
Toward Faithful Case-based Reasoning through Learning Prototypes in a Nearest Neighbor-friendly Space
Towards A Unified Policy Abstraction Theory and Representation Learning Approach in Markov Decision Processes
Towards a Unified View of Parameter-Efficient Transfer Learning
Towards a Unified View on Visual Parameter-Efficient Transfer Learning
Towards Better Understanding and Better Generalization of Low-shot Classification in Histology Images with Contrastive Learning
Towards Building A Group-based Unsupervised Representation Disentanglement Framework
Towards Coherent and Consistent Use of Entities in Narrative Generation
Towards Continual Knowledge Learning of Language Models
Towards Deepening Graph Neural Networks: A GNTK-based Optimization Perspective
Towards Demystifying Representation Learning with Non-contrastive Self-supervision
Towards Deployment-Efficient Reinforcement Learning: Lower Bound and Optimality
Towards Empirical Sandwich Bounds on the Rate-Distortion Function
Towards Evaluating the Robustness of Neural Networks Learned by Transduction
Towards Fair Classification against Poisoning Attacks
Towards fast and effective single-step adversarial training
Towards Federated Learning on Time-Evolving Heterogeneous Data
Towards General Function Approximation in Zero-Sum Markov Games
Towards Generalizable Personalized Federated Learning with Adaptive Local Adaptation
Towards General Robustness to Bad Training Data
Towards Generative Latent Variable Models for Speech
Towards Generic Interface for Human-Neural Network Knowledge Exchange
Towards Learning to Speak and Hear Through Multi-Agent Communication over a Continuous Acoustic Channel
Towards Model Agnostic Federated Learning Using Knowledge Distillation
Towards Scheduling Federated Deep Learning using Meta-Gradients for Inter-Hospital Learning
Towards simple time-to-event modeling: optimizing neural networks via rank regression
Towards Structured Dynamic Sparse Pre-Training of BERT
Towards Sustainable Self-supervised Learning
Towards the Memorization Effect of Neural Networks in Adversarial Training
Towards Training Billion Parameter Graph Neural Networks for Atomic Simulations
Towards Uncertainties in Deep Learning that Are Accurate and Calibrated
Towards Understanding Distributional Reinforcement Learning: Regularization, Optimization, Acceleration and Sinkhorn Algorithm
Towards Understanding Generalization via Decomposing Excess Risk Dynamics
Towards Understanding How Machines Can Learn Causal Overhypotheses
Towards understanding how momentum improves generalization in deep learning
Towards Understanding Label Smoothing
Towards Understanding the Data Dependency of Mixup-style Training
Towards Understanding the Robustness Against Evasion Attack on Categorical Data
Towards Unsupervised Content Disentanglement in Sentence Representations via Syntactic Roles
TPU-GAN: Learning temporal coherence from dynamic point cloud sequences
Tracking the risk of a deployed model and detecting harmful distribution shifts

« prev Page 43/47 next »