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
Tractable Dendritic RNNs for Identifying Unknown Nonlinear Dynamical Systems
Trading Coverage for Precision: Conformal Prediction with Limited False Discoveries
Trading Quality for Efficiency of Graph Partitioning: An Inductive Method across Graphs
TRAIL: Near-Optimal Imitation Learning with Suboptimal Data
Training Data Generating Networks: Shape Reconstruction via Bi-level Optimization
Training Data Size Induced Double Descent For Denoising Neural Networks and the Role of Training Noise Level
Training-Free Robust Multimodal Learning via Sample-Wise Jacobian Regularization
Training invariances and the low-rank phenomenon: beyond linear networks
Training Multi-Layer Over-Parametrized Neural Network in Subquadratic Time
Training Structured Neural Networks Through Manifold Identification and Variance Reduction
Training Transition Policies via Distribution Matching for Complex Tasks
Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation
TRAKR – A reservoir-based tool for fast and accurate classification of neural time-series patterns
Transductive Universal Transport for Zero-Shot Action Recognition
Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations
Transferable Adversarial Attack based on Integrated Gradients
Transfer Learning for Bayesian HPO with End-to-End Meta-Features
Transfer Learning with Pre-trained Conditional Generative Models
Transferring Hierarchical Structure with Dual Meta Imitation Learning
Transfer RL across Observation Feature Spaces via Model-Based Regularization
Transform2Act: Learning a Transform-and-Control Policy for Efficient Agent Design
Transformed CNNs: recasting pre-trained convolutional layers with self-attention
Transformer-based Transform Coding
Transformers are Meta-Reinforcement Learners
Transformers Can Do Bayesian Inference
Transformer with a Mixture of Gaussian Keys
Transition to Linearity of Wide Neural Networks is an Emerging Property of Assembling Weak Models
Translating Robot Skills: Learning Unsupervised Skill Correspondences Across Robots
Transliteration: A Simple Technique For Improving Multilingual Language Modeling
TransSlowDown: Efficiency Attacks on Neural Machine Translation Systems
TRGP: Trust Region Gradient Projection for Continual Learning
Triangle and Four Cycle Counting with Predictions in Graph Streams
Trident Pyramid Networks: The importance of processing at the feature pyramid level for better object detection
Trigger Hunting with a Topological Prior for Trojan Detection
Trivial or Impossible --- dichotomous data difficulty masks model differences (on ImageNet and beyond)
Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning
Truth Table Deep Convolutional Neural Network, A New SAT-Encodable Architecture - Application To Complete Robustness
Tuformer: Data-driven Design of Transformers for Improved Generalization or Efficiency
T-WaveNet: A Tree-Structured Wavelet Neural Network for Time Series Signal Analysis
Two Birds, One Stone: Achieving both Differential Privacy and Certified Robustness for Pre-trained Classifiers via Input Perturbation
Two-Dimensional Weisfeiler-Lehman Graph Neural Networks for Link Prediction
Two Instances of Interpretable Neural Network for Universal Approximations
Two Regimes of Generalization for Non-Linear Metric Learning
Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks
Uncertainty-Aware Deep Video Compression with Ensembles
Uncertainty-based out-of-distribution detection requires suitable function space priors
Uncertainty Modeling for Out-of-Distribution Generalization
Unconditional Diffusion Guidance
Understanding AdamW through Proximal Methods and Scale-Freeness
Understanding and Improving Graph Injection Attack by Promoting Unnoticeability

« prev Page 44/47 next »