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
Exploiting Minimum-Variance Policy Evaluation for Policy Optimization
Explore and Control with Adversarial Surprise
Exploring and Evaluating Personalized Models for Code Generation
Exploring Covariate and Concept Shift for Detection and Confidence Calibration of Out-of-Distribution Data
Exploring extreme parameter compression for pre-trained language models
Exploring Memorization in Adversarial Training
Exploring Non-Contrastive Representation Learning for Deep Clustering
Exploring the Limits of Large Scale Pre-training
Exposing the Implicit Energy Networks behind Masked Language Models via Metropolis--Hastings
Expressiveness and Approximation Properties of Graph Neural Networks
Expressivity of Emergent Languages is a Trade-off between Contextual Complexity and Unpredictability
ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning
Extending the WILDS Benchmark for Unsupervised Adaptation
F8Net: Fixed-Point 8-bit Only Multiplication for Network Quantization
FaceDet3D: Facial Expressions with 3D Geometric Detail Hallucination
Fact-driven Logical Reasoning
Factored World Models for Zero-Shot Generalization in Robotic Manipulation
FairCal: Fairness Calibration for Face Verification
Fairness Guarantees under Demographic Shift
Fairness in Representation for Multilingual NLP: Insights from Controlled Experiments on Conditional Language Modeling
Fair Node Representation Learning via Adaptive Data Augmentation
Fair Normalizing Flows
FALCON: Fast Visual Concept Learning by Integrating Images, Linguistic descriptions, and Conceptual Relations
FARE: Provably Fair Representation Learning
Fast Adaptive Anomaly Detection
Fast AdvProp
Fast and Efficient Once-For-All Networks for Diverse Hardware Deployment
Fast and Sample-Efficient Domain Adaptation for Autoencoder-Based End-to-End Communication
Fast Deterministic Stackelberg Actor-Critic
Fast Differentiable Matrix Square Root
Faster No-Regret Learning Dynamics for Extensive-Form Correlated Equilibrium
Faster Reinforcement Learning with Value Target Lower Bounding
Fast Finite Width Neural Tangent Kernel
Fast Generic Interaction Detection for Model Interpretability and Compression
Fast Model Editing at Scale
Fast Regression for Structured Inputs
FastRPB: a Scalable Relative Positional Encoding for Long Sequence Tasks
FastSHAP: Real-Time Shapley Value Estimation
Fast topological clustering with Wasserstein distance
FCause: Flow-based Causal Discovery
Feasible Adversarial Robust Reinforcement Learning for Underspecified Environments
Feature Flow Regularization: Improving Structured Sparsity in Deep Neural Networks
Feature Kernel Distillation
Feature Selection in the Contrastive Analysis Setting
FED-$\chi^2$: Secure Federated Correlation Test
FedBABU: Toward Enhanced Representation for Federated Image Classification
FedChain: Chained Algorithms for Near-optimal Communication Cost in Federated Learning
FedDiscrete: A Secure Federated Learning Algorithm Against Weight Poisoning
FedDrop: Trajectory-weighted Dropout for Efficient Federated Learning
Federated Inference through Aligning Local Representations and Learning a Consensus Graph

« prev Page 15/47 next »