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
Federated Learning for Inference at Anytime and Anywhere
FEDERATED LEARNING FRAMEWORK BASED ON TRIMMED MEAN AGGREGATION RULES
Federated Learning from Only Unlabeled Data with Class-conditional-sharing Clients
Federated Learning on Adaptively Weighted Nodes by Bilevel Optimization
Federated Learning via Plurality Vote
Federated Learning with GAN-based Data Synthesis for Non-IID Clients
Federated Learning with Heterogeneous Architectures using Graph HyperNetworks
Federated Learning with Partial Model Personalization
Federated Robustness Propagation: Sharing Adversarial Robustness in Federated Learning
FedGEMS: Federated Learning of Larger Server Models via Selective Knowledge Fusion
FedLite: A Scalable Approach for Federated Learning on Resource-constrained Clients
FedMT: Federated Learning with Mixed-type Labels
FedNAS: Federated Deep Learning via Neural Architecture Search
FedorAS: Federated Architecture Search under system heterogeneity
FedPAGE: A Fast Local Stochastic Gradient Method for Communication-Efficient Federated Learning
FedPara: Low-rank Hadamard Product for Communication-Efficient Federated Learning
FedProf: Selective Federated Learning with Representation Profiling
Feudal Reinforcement Learning by Reading Manuals
Few-Shot Attribute Learning
Few-Shot Backdoor Attacks on Visual Object Tracking
Few-Shot Classification with Task-Adaptive Semantic Feature Learning
Few-shot graph link prediction with domain adaptation
Few-shot Learning via Dirichlet Tessellation Ensemble
Few-shot Learning with Big Prototypes
FiD-Light: Efficient and Effective Retrieval-Augmented Text Generation
Fieldwise Factorized Networks for Tabular Data Classification
Fight fire with fire: countering bad shortcuts in imitation learning with good shortcuts
FILIP: Fine-grained Interactive Language-Image Pre-Training
Filling the G_ap_s: Multivariate Time Series Imputation by Graph Neural Networks
FILM: Following Instructions in Language with Modular Methods
Filtered-CoPhy: Unsupervised Learning of Counterfactual Physics in Pixel Space
Finding an Unsupervised Image Segmenter in each of your Deep Generative Models
Finding Biological Plausibility for Adversarially Robust Features via Metameric Tasks
Finding General Equilibria in Many-Agent Economic Simulations using Deep Reinforcement Learning
Finding lost DG: Explaining domain generalization via model complexity
Finding One Missing Puzzle of Contextual Word Embedding: Representing Contexts as Manifold
Fine-grained Differentiable Physics: A Yarn-level Model for Fabrics
Finetuned Language Models are Zero-Shot Learners
Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution
Finite-Time Convergence and Sample Complexity of Multi-Agent Actor-Critic Reinforcement Learning with Average Reward
Finite-Time Error Bounds for Distributed Linear Stochastic Approximation
First-Order Optimization Inspired from Finite-Time Convergent Flows
FitVid: High-Capacity Pixel-Level Video Prediction
Fixed Neural Network Steganography: Train the images, not the network
FLAME-in-NeRF: Neural control of Radiance Fields for Free View Face Animation
Flashlight: Enabling Innovation in Tools for Machine Learning
FlexConv: Continuous Kernel Convolutions With Differentiable Kernel Sizes
Flow-based Recurrent Belief State Learning for POMDPs
FlowX: Towards Explainable Graph Neural Networks via Message Flows
Focus on the Common Good: Group Distributional Robustness Follows

« prev Page 16/47 next »