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
Distribution Matching in Deep Generative Models with Kernel Transfer Operators
Diurnal or Nocturnal? Federated Learning of Multi-branch Networks from Periodically Shifting Distributions
DIVA: Dataset Derivative of a Learning Task
Dive Deeper Into Integral Pose Regression
Divergence-aware Federated Self-Supervised Learning
Divergence-Regularized Multi-Agent Actor-Critic
Divergent representations of ethological visual inputs emerge from supervised, unsupervised, and reinforcement learning
Diverse and Consistent Multi-view Networks for Semi-supervised Regression
Diverse Client Selection for Federated Learning via Submodular Maximization
DIVERSIFY to Generalize: Learning Generalized Representations for Time Series Classification
Divide and Explore: Multi-Agent Separate Exploration with Shared Intrinsic Motivations
Divisive Feature Normalization Improves Image Recognition Performance in AlexNet
DKM: Differentiable k-Means Clustering Layer for Neural Network Compression
DNN Quantization with Attention
Do deep networks transfer invariances across classes?
Does Entity Abstraction Help Generative Transformers Reason?
Does your graph need a confidence boost? Convergent boosted smoothing on graphs with tabular node features
Domain-Adjusted Regression or: ERM May Already Learn Features Sufficient for Out-of-Distribution Generalization
Domain Adversarial Training: A Game Perspective
Domain-wise Adversarial Training for Out-of-Distribution Generalization
Dominant Datapoints and the Block Structure Phenomenon in Neural Network Hidden Representations
Domino: Discovering Systematic Errors with Cross-Modal Embeddings
Do Not Escape From the Manifold: Discovering the Local Coordinates on the Latent Space of GANs
Double Descent in Adversarial Training: An Implicit Label Noise Perspective
Doubly Adaptive Scaled Algorithm for Machine Learning Using Second-Order Information
Do Users Benefit From Interpretable Vision? A User Study, Baseline, And Dataset
Do We Need Anisotropic Graph Neural Networks?
Do What Nature Did To Us: Evolving Plastic Recurrent Neural Networks For Generalized Tasks
Downstream Datasets Make Surprisingly Good Pretraining Corpora
DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models
DPP-TTS: Diversifying prosodic features of speech via determinantal point processes
DP-REC: Private & Communication-Efficient Federated Learning
DR3: Value-Based Deep Reinforcement Learning Requires Explicit Regularization
DreamerPro: Reconstruction-Free Model-Based Reinforcement Learning with Prototypical Representations
DriPP: Driven Point Processes to Model Stimuli Induced Patterns in M/EEG Signals
Dropout Q-Functions for Doubly Efficient Reinforcement Learning
DSEE: Dually Sparsity-embedded Efficient Tuning of Pre-trained Language Models
Dual Lottery Ticket Hypothesis
Dual Training of Energy-Based Models with Overparametrized Shallow Neural Networks
Dynamical Isometry for Residual Networks
Dynamic and Efficient Gray-Box Hyperparameter Optimization for Deep Learning
Dynamic Graph Representation Learning via Graph Transformer Networks
Dynamic Least-Squares Regression
Dynamic Parameterized Network for CTR Prediction
Dynamics-Aware Comparison of Learned Reward Functions
Dynamic Token Normalization improves Vision Transformers
E$^2$CM: Early Exit via Class Means for Efficient Supervised and Unsupervised Learning
EAT-C: Environment-Adversarial sub-Task Curriculum for Efficient Reinforcement Learning
EBM Life Cycle: MCMC Strategies for Synthesis, Defense, and Density Modeling
ED2: An Environment Dynamics Decomposition Framework for World Model Construction

« prev Page 12/47 next »