AAAI 2022

1,685 papers

Top Research Directions

Research directions most represented by AAAI 2022 papers.

Over-Smoothing in Graph Neural Networks 14
Bypassing the Computational Bottleneck of Adversarial Training 12
Overcoming the Homophily Assumption in Graph Neural Networks 11
Loss Weighting via Predictive Uncertainty 10
Fair Division of Indivisible Resources 10
Clean Accuracy Degradation in Machine Learning Defenses 9
Scaling Visual Attention Beyond Quadratic Complexity 9
Semantic Collision and False Negatives in Contrastive Learning 8
Disentangling Attribute Control in Generative Models 8
Self Supervised Pretraining for High Stakes Label Efficiency 8
Adversarial Training for Domain Invariant Representations 8
Safe Reinforcement Learning via Constrained Markov Decision Processes 8
The Pareto Frontier of Algorithmic Accuracy and Fairness 8
The Non-Linear Function Approximation Gap in Reinforcement Learning 8
The Cross Modal Representation Gap 8

Top Authors

AuthorPapers
Fan Zhou8
Ting Zhong7
Pin-Yu Chen6
Han Yu5
Kunpeng Zhang5
Milind Tambe5
Zheng-Jun Zha5
Chang-Tien Lu4
Goce Trajcevski4
Heng Huang4
Houqiang Li4
Ioannis Caragiannis4
Jiaoyang Li4
Jie Song4
Liang Zhao4
Lizhuang Ma4
Nanning Zheng4
Peter J. Stuckey4
Shouhong Ding4
Sven Koenig4

Impactful Papers

Papers from AAAI 2022 that shaped research clusters.

Foundational

Influential

Papers

Title
Robust Rule Learning for Reliable and Interpretable Insight into Expertise Transfer Opportunities
Robust Tests in Online Decision-Making
Role of Human-AI Interaction in Selective Prediction
RRL: Regional Rotate Layer in Convolutional Neural Networks
Rushing and Strolling among Answer Sets - Navigation Made Easy
Safe Distillation Box
Safe Online Convex Optimization with Unknown Linear Safety Constraints
Safe Subgame Resolving for Extensive Form Correlated Equilibrium
SAIL: Self-Augmented Graph Contrastive Learning
Saliency Grafting: Innocuous Attribution-Guided Mixup with Calibrated Label Mixing
Same State, Different Task: Continual Reinforcement Learning without Interference
Sample Average Approximation for Stochastic Optimization with Dependent Data: Performance Guarantees and Tractability
Sample-Efficient Iterative Lower Bound Optimization of Deep Reactive Policies for Planning in Continuous MDPs
Sample-Efficient Reinforcement Learning via Conservative Model-Based Actor-Critic
Sampling and Counting Acyclic Orientations in Chordal Graphs (Student Abstract)
Sampling-Based Robust Control of Autonomous Systems with Non-Gaussian Noise
SASA: Semantics-Augmented Set Abstraction for Point-Based 3D Object Detection
SAS: Self-Augmentation Strategy for Language Model Pre-training
Saving Stochastic Bandits from Poisoning Attacks via Limited Data Verification
Scaled ReLU Matters for Training Vision Transformers
Scaling Neural Program Synthesis with Distribution-Based Search
Scaling Up Influence Functions
SCALoss: Side and Corner Aligned Loss for Bounding Box Regression
SCAN: Cross Domain Object Detection with Semantic Conditioned Adaptation
SCIR-Net: Structured Color Image Representation Based 3D Object Detection Network from Point Clouds
SCRIB: Set-Classifier with Class-Specific Risk Bounds for Blackbox Models
SCSNet: An Efficient Paradigm for Learning Simultaneously Image Colorization and Super-resolution
SCTN: Sparse Convolution-Transformer Network for Scene Flow Estimation
Search and Learn: Improving Semantic Coverage for Data-to-Text Generation
Search Strategies for Topological Network Optimization
Secretary Matching with Vertex Arrivals and No Rejections
SECRET: Self-Consistent Pseudo Label Refinement for Unsupervised Domain Adaptive Person Re-identification
SEFormer: Structure Embedding Transformer for 3D Object Detection
Seizing Critical Learning Periods in Federated Learning
Selecting Optimal Context Sentences for Event-Event Relation Extraction
Self-Adaptive Imitation Learning: Learning Tasks with Delayed Rewards from Sub-optimal Demonstrations
Self-Labeling Framework for Novel Category Discovery over Domains
Self-Supervised Audio-and-Text Pre-training with Extremely Low-Resource Parallel Data
Self-Supervised Category-Level 6D Object Pose Estimation with Deep Implicit Shape Representation
Self-Supervised Enhancement of Latent Discovery in GANs
Self-Supervised Graph Neural Networks via Diverse and Interactive Message Passing
Self-Supervised Knowledge Assimilation for Expert-Layman Text Style Transfer
Self-Supervised Object Localization with Joint Graph Partition
Self-Supervised Pre-training for Protein Embeddings Using Tertiary Structures
Self-Supervised Pretraining for RGB-D Salient Object Detection
Self-Supervised Representation Learning Framework for Remote Physiological Measurement Using Spatiotemporal Augmentation Loss
Self-Supervised Robust Scene Flow Estimation via the Alignment of Probability Density Functions
Self-Supervised Spatiotemporal Representation Learning by Exploiting Video Continuity
Self-Training Multi-Sequence Learning with Transformer for Weakly Supervised Video Anomaly Detection
Semantically Contrastive Learning for Low-Light Image Enhancement

« prev Page 27/34 next »