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
Mix-MaxEnt: Creating High Entropy Barriers To Improve Accuracy and Uncertainty Estimates of Deterministic Neural Networks
MixRL: Data Mixing Augmentation for Regression using Reinforcement Learning
Mixture Representation Learning with Coupled Autoencoders
MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer
Model Agnostic Interpretability for Multiple Instance Learning
Model-Agnostic Meta-Attack: Towards Reliable Evaluation of Adversarial Robustness
Model-augmented Prioritized Experience Replay
Model-Based Offline Meta-Reinforcement Learning with Regularization
Model-based Reinforcement Learning with a Hamiltonian Canonical ODE Network
Model-Based Robust Adaptive Semantic Segmentation
Model Compression via Symmetries of the Parameter Space
Model-Efficient Deep Learning with Kernelized Classification
Model Fusion of Heterogeneous Neural Networks via Cross-Layer Alignment
Modeling Adversarial Noise for Adversarial Defense
Modeling Label Space Interactions in Multi-label Classification using Box Embeddings
Model-Invariant State Abstractions for Model-Based Reinforcement Learning
Modelling neuronal behaviour with time series regression: Recurrent Neural Networks on synthetic C. elegans data
Model Validation Using Mutated Training Labels: An Exploratory Study
Model Zoo: A Growing Brain That Learns Continually
ModeRNN: Harnessing Spatiotemporal Mode Collapse in Unsupervised Predictive Learning
Modular Lifelong Reinforcement Learning via Neural Composition
Molecular Graph Representation Learning via Heterogeneous Motif Graph Construction
Momentum Conserving Lagrangian Neural Networks
Momentum Contrastive Autoencoder: Using Contrastive Learning for Latent Space Distribution Matching in WAE
Momentum Doesn't Change The Implicit Bias
MonoDistill: Learning Spatial Features for Monocular 3D Object Detection
Monotone deep Boltzmann machines
Monotonic Differentiable Sorting Networks
Monotonic Improvement Guarantees under Non-stationarity for Decentralized PPO
Monotonicity as a requirement and as a regularizer: efficient methods and applications
MoReL: Multi-omics Relational Learning
Motion Planning Transformers: One Model to Plan them All
MQTransformer: Multi-Horizon Forecasts with Context Dependent and Feedback-Aware Attention
MS$^2$-Transformer: An End-to-End Model for MS/MS-assisted Molecule Identification
MT3: Multi-Task Multitrack Music Transcription
MT-GBM: A Multi-Task Gradient Boosting Machine with Shared Decision Trees
Multi-Agent Constrained Policy Optimisation
Multi-Agent Language Learning: Symbolic Mapping
Multi-Agent MDP Homomorphic Networks
Multi-agent Performative Prediction: From Global Stability and Optimality to Chaos
Multi-Agent Reinforcement Learning with Shared Resource in Inventory Management
Multi-Agent Reinforcement Learning with Shared Resources for Inventory Management
Multi-batch Reinforcement Learning via Sample Transfer and Imitation Learning
Multi-Critic Actor Learning: Teaching RL Policies to Act with Style
Multi-Domain Self-Supervised Learning
Multi-hypothesis 3D human pose estimation metrics favor miscalibrated distributions
Multilevel physics informed neural networks (MPINNs)
Multimeasurement Generative Models
Multi-modal Self-supervised Pre-training for Regulatory Genome Across Cell Types
Multi-Mode Deep Matrix and Tensor Factorization

« prev Page 28/47 next »