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
Sample Efficient Stochastic Policy Extragradient Algorithm for Zero-Sum Markov Game
Sample Selection with Uncertainty of Losses for Learning with Noisy Labels
Sampling from Discrete Energy-Based Models with Quality/Efficiency Trade-offs
Sampling with Mirrored Stein Operators
SANE: Specialization-Aware Neural Network Ensemble
Scalable Hierarchical Embeddings of Complex Networks
Scalable multimodal variational autoencoders with surrogate joint posterior
Scalable One-Pass Optimisation of High-Dimensional Weight-Update Hyperparameters by Implicit Differentiation
Scalable Robust Federated Learning with Provable Security Guarantees
Scalable Sampling for Nonsymmetric Determinantal Point Processes
ScaLA: Speeding-Up Fine-tuning of Pre-trained Transformer Networks via Efficient and Scalable Adversarial Perturbation
Scale Efficiently: Insights from Pretraining and Finetuning Transformers
Scale Mixtures of Neural Network Gaussian Processes
Scaling Densities For Improved Density Ratio Estimation
Scaling Fair Learning to Hundreds of Intersectional Groups
Scaling Laws for Neural Machine Translation
Scaling-up Diverse Orthogonal Convolutional Networks by a Paraunitary Framework
Scarf: Self-Supervised Contrastive Learning using Random Feature Corruption
Scattering Networks on the Sphere for Scalable and Rotationally Equivariant Spherical CNNs
Scene Transformer: A unified architecture for predicting future trajectories of multiple agents
SCformer: Segment Correlation Transformer for Long Sequence Time Series Forecasting
ScheduleNet: Learn to solve multi-agent scheduling problems with reinforcement learning
Score-Based Generative Modeling with Critically-Damped Langevin Diffusion
SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations
Second-Order Unsupervised Feature Selection via Knowledge Contrastive Distillation
Secure Distributed Training at Scale
SegTime: Precise Time Series Segmentation without Sliding Window
Selective Ensembles for Consistent Predictions
Selective Token Generation for Few-shot Language Modeling
Self-consistent Gradient-like Eigen Decomposition in Solving Schrödinger Equations
Self-Contrastive Learning
Self-ensemble Adversarial Training for Improved Robustness
Self-GenomeNet: Self-supervised Learning with Reverse-Complement Context Prediction for Nucleotide-level Genomics Data
Self-Joint Supervised Learning
Self Reward Design with Fine-grained Interpretability
Self-Supervised Graph Neural Networks for Improved Electroencephalographic Seizure Analysis
Self-Supervised Inference in State-Space Models
Self-supervised Learning for Sequential Recommendation with Model Augmentation
Self-supervised Learning is More Robust to Dataset Imbalance
Self-supervised regression learning using domain knowledge: Applications to improving self-supervised image denoising
Self-Supervised Representation Learning via Latent Graph Prediction
Self-Supervised Structured Representations for Deep Reinforcement Learning
Self-Supervise, Refine, Repeat: Improving Unsupervised Anomaly Detection
Self-Supervision Enhanced Feature Selection with Correlated Gates
Semantically Controllable Generation of Physical Scenes with Explicit Knowledge
Semi-Empirical Objective Functions for Neural MCMC Proposal Optimization
Semi-relaxed Gromov-Wasserstein divergence and applications on graphs
SemiRetro: Semi-template framework boosts deep retrosynthesis prediction
Semi-supervised learning objectives as log-likelihoods in a generative model of data curation
Semi-supervised learning of partial differential operators and dynamical flows

« prev Page 38/47 next »