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
PandA: Unsupervised Learning of Parts and Appearances in the Feature Maps of GANs
Parallel Deep Neural Networks Have Zero Duality Gap
Parallel Training of GRU Networks with a Multi-Grid Solver for Long Sequences
Pareto Navigation Gradient Descent: a First Order Algorithm for Optimization in Pareto Set
Pareto Policy Adaptation
Pareto Policy Pool for Model-based Offline Reinforcement Learning
Pareto Set Learning for Neural Multi-Objective Combinatorial Optimization
PARL: Enhancing Diversity of Ensemble Networks to Resist Adversarial Attacks via Pairwise Adversarially Robust Loss Function
PARS: PSEUDO-LABEL AWARE ROBUST SAMPLE SELECTION FOR LEARNING WITH NOISY LABELS
Partial Information as Full: Reward Imputation with Sketching in Bandits
Partial Wasserstein Adversarial Network for Non-rigid Point Set Registration
Particle Based Stochastic Policy Optimization
Particle Stochastic Dual Coordinate Ascent: Exponential convergent algorithm for mean field neural network optimization
Patches Are All You Need?
Patch-Fool: Are Vision Transformers Always Robust Against Adversarial Perturbations?
Path Auxiliary Proposal for MCMC in Discrete Space
Path Integral Sampler: A Stochastic Control Approach For Sampling
Path-specific Causal Fair Prediction via Auxiliary Graph Structure Learning
PDQN - A Deep Reinforcement Learning Method for Planning with Long Delays: Optimization of Manufacturing Dispatching
PEARL: Data Synthesis via Private Embeddings and Adversarial Reconstruction Learning
Peek-a-Boo: What (More) is Disguised in a Randomly Weighted Neural Network, and How to Find It Efficiently
Perceiver IO: A General Architecture for Structured Inputs & Outputs
PER-ETD: A Polynomially Efficient Emphatic Temporal Difference Learning Method
Permutation-Based SGD: Is Random Optimal?
Permutation Compressors for Provably Faster Distributed Nonconvex Optimization
Permutation invariant graph-to-sequence model for template-free retrosynthesis and reaction prediction
Personalized Federated Hypernetworks for Privacy Preservation in Multi-Task Reinforcement Learning
PERSONALIZED LAB TEST RESPONSE PREDICTION WITH KNOWLEDGE AUGMENTATION
Personalized Neural Architecture Search for Federated Learning
Perturbation Deterioration: The Other Side of Catastrophic Overfitting
Pessimistic Bootstrapping for Uncertainty-Driven Offline Reinforcement Learning
Pessimistic Model-based Offline Reinforcement Learning under Partial Coverage
PF-GNN: Differentiable particle filtering based approximation of universal graph representations
Phase Collapse in Neural Networks
PhaseFool: Phase-oriented Audio Adversarial Examples via Energy Dissipation
Phenomenology of Double Descent in Finite-Width Neural Networks
Physical Gradients for Deep Learning
Physics Informed Machine Learning of SPH: Machine Learning Lagrangian Turbulence
Physics-Informed Neural Operator for Learning Partial Differential Equations
PI3NN: Out-of-distribution-aware Prediction Intervals from Three Neural Networks
Picking Daisies in Private: Federated Learning from Small Datasets
PiCO: Contrastive Label Disambiguation for Partial Label Learning
PI-GNN: Towards Robust Semi-Supervised Node Classification against Noisy Labels
PipeGCN: Efficient Full-Graph Training of Graph Convolutional Networks with Pipelined Feature Communication
PIVQGAN: Posture and Identity Disentangled Image-to-Image Translation via Vector Quantization
Pix2seq: A Language Modeling Framework for Object Detection
Pixelated Butterfly: Simple and Efficient Sparse training for Neural Network Models
PKCAM: Previous Knowledge Channel Attention Module
Plan Better Amid Conservatism: Offline Multi-Agent Reinforcement Learning with Actor Rectification
Planckian jitter: enhancing the color quality of self-supervised visual representations

« prev Page 33/47 next »