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
Edge Partition Modulated Graph Convolutional Networks
Edge Rewiring Goes Neural: Boosting Network Resilience via Policy Gradient
EE-Net: Exploitation-Exploration Neural Networks in Contextual Bandits
EF21 with Bells & Whistles: Practical Algorithmic Extensions of Modern Error Feedback
Effective Model Sparsification by Scheduled Grow-and-Prune Methods
Effective Polynomial Filter Adaptation for Graph Neural Networks
Effective Uncertainty Estimation with Evidential Models for Open-World Recognition
Effect of scale on catastrophic forgetting in neural networks
Effects of Data Geometry in Early Deep Learning
Efficient Active Search for Combinatorial Optimization Problems
Efficient and Differentiable Conformal Prediction with General Function Classes
Efficient Automatic Machine Learning via Design Graphs
Efficient Certification for Probabilistic Robustness
Efficient Computation of Deep Nonlinear Infinite-Width Neural Networks that Learn Features
Efficient Image Representation Learning with Federated Sampled Softmax
Efficient Learning of Safe Driving Policy via Human-AI Copilot Optimization
Efficiently Modeling Long Sequences with Structured State Spaces
Efficient Neural Causal Discovery without Acyclicity Constraints
Efficient Out-of-Distribution Detection via CVAE data Generation
EfficientPhys: Enabling Simple, Fast, and Accurate Camera-Based Vitals Measurement
Efficient representations for privacy-preserving inference
Efficient Sharpness-aware Minimization for Improved Training of Neural Networks
Efficient Split-Mix Federated Learning for On-Demand and In-Situ Customization
Efficient Token Mixing for Transformers via Adaptive Fourier Neural Operators
Efficient Training and Inference of Hypergraph Reasoning Networks
Efficient Wasserstein and Sinkhorn Policy Optimization
Eigencurve: Optimal Learning Rate Schedule for SGD on Quadratic Objectives with Skewed Hessian Spectrums
EigenGame Unloaded: When playing games is better than optimizing
Eigenspace Restructuring: a Principle of Space and Frequency in Neural Networks
Eigenvalue Initialisation and Regularisation for Koopman Autoencoders
Einops: Clear and Reliable Tensor Manipulations with Einstein-like Notation
EinSteinVI: General and Integrated Stein Variational Inference
Eliminating Sharp Minima from SGD with Truncated Heavy-tailed Noise
Embedded-model flows: Combining the inductive biases of model-free deep learning and explicit probabilistic modeling
Embedding Compression with Hashing for Efficient Representation Learning in Graph
Embedding models through the lens of Stable Coloring
Emergent Communication at Scale
Empirical Study of the Decision Region and Robustness in Deep Neural Networks
Enabling Arbitrary Translation Objectives with Adaptive Tree Search
Encoding Event-Based Gesture Data With a Hybrid SNN Guided Variational Auto-encoder
Encoding Hierarchical Information in Neural Networks Helps in Subpopulation Shift
Encoding Weights of Irregular Sparsity for Fixed-to-Fixed Model Compression
End-to-End Learning of Probabilistic Hierarchies on Graphs
Energy-Based Learning for Cooperative Games, with Applications to Valuation Problems in Machine Learning
Energy-Inspired Molecular Conformation Optimization
Enforcing fairness in private federated learning via the modified method of differential multipliers
Enforcing physics-based algebraic constraints for inference of PDE models on unstructured grids
Enhancing Cross-lingual Transfer by Manifold Mixup
Enhancing semi-supervised learning via self-interested coalitional learning
Ensemble-in-One: Learning Ensemble within Random Gated Networks for Enhanced Adversarial Robustness

« prev Page 13/47 next »