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
Planning in Stochastic Environments with a Learned Model
Plant 'n' Seek: Can You Find the Winning Ticket?
PMIC: Improving Multi-Agent Reinforcement Learning with Progressive Mutual Information Collaboration
POETREE: Interpretable Policy Learning with Adaptive Decision Trees
Poisoned classifiers are not only backdoored, they are fundamentally broken
Poisoning and Backdooring Contrastive Learning
Policy Gradients Incorporating the Future
Policy improvement by planning with Gumbel
Policy Smoothing for Provably Robust Reinforcement Learning
PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functions
PoNet: Pooling Network for Efficient Token Mixing in Long Sequences
Positive-Unlabeled Learning with Uncertainty-aware Pseudo-label Selection
Possibility Before Utility: Learning And Using Hierarchical Affordances
Post hoc Explanations may be Ineffective for Detecting Unknown Spurious Correlation
Post-Training Detection of Backdoor Attacks for Two-Class and Multi-Attack Scenarios
Post-Training Quantization Is All You Need to Perform Cross-Platform Learned Image Compression
Practical Adversarial Attacks on Brain--Computer Interfaces
Practical and Private Heterogeneous Federated Learning
Practical Conditional Neural Process Via Tractable Dependent Predictions
Practical Integration via Separable Bijective Networks
Predicting Physics in Mesh-reduced Space with Temporal Attention
Predicting subscriber usage: Analyzing multi-dimensional time-series using Convolutional Neural Networks
Pretext Tasks Selection for Multitask Self-Supervised Speech Representation Learning
Pretrained Language Model in Continual Learning: A Comparative Study
Pretrained models are active learners
Pretraining for Language Conditioned Imitation with Transformers
Pretraining Text Encoders with Adversarial Mixture of Training Signal Generators
PRIMA: Planner-Reasoner Inside a Multi-task Reasoning Agent
PriorGrad: Improving Conditional Denoising Diffusion Models with Data-Dependent Adaptive Prior
Prioritized training on points that are learnable, worth learning, and not yet learned
Privacy Auditing of Machine Learning using Membership Inference Attacks
Privacy Implications of Shuffling
Privacy-preserving Task-Agnostic Vision Transformer for Image Processing
Private Multi-Winner Voting For Machine Learning
Probabilistic Implicit Scene Completion
Probability flow solution of the Fokker-Planck equation
Procedural generalization by planning with self-supervised world models
Programmable 3D snapshot microscopy with Fourier convolutional networks
Programmatic Reinforcement Learning without Oracles
Progressive Distillation for Fast Sampling of Diffusion Models
Promoting Saliency From Depth: Deep Unsupervised RGB-D Saliency Detection
Proof Artifact Co-Training for Theorem Proving with Language Models
Propagating Distributions through Neural Networks
Properties from mechanisms: an equivariance perspective on identifiable representation learning
Prospect Pruning: Finding Trainable Weights at Initialization using Meta-Gradients
Protect the weak: Class focused online learning for adversarial training
Protein structure generation via folding diffusion
ProtoRes: Proto-Residual Network for Pose Authoring via Learned Inverse Kinematics
Prototype Based Classification from Hierarchy to Fairness
Prototype memory and attention mechanisms for few shot image generation

« prev Page 34/47 next »