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
Constraint-Driven Explanations for Black-Box ML Models
Constraint Sampling Reinforcement Learning: Incorporating Expertise for Faster Learning
Constraints Penalized Q-learning for Safe Offline Reinforcement Learning
Construct Effective Geometry Aware Feature Pyramid Network for Multi-Scale Object Detection
Contact-Distil: Boosting Low Homologous Protein Contact Map Prediction by Self-Supervised Distillation
Content-Variant Reference Image Quality Assessment via Knowledge Distillation
Context-Aware Health Event Prediction via Transition Functions on Dynamic Disease Graphs
Context-Aware Transfer Attacks for Object Detection
Context-Based Contrastive Learning for Scene Text Recognition
Context-Specific Representation Abstraction for Deep Option Learning
Context Uncertainty in Contextual Bandits with Applications to Recommender Systems
Continual Learning through Retrieval and Imagination
Continuous Mixtures of Tractable Probabilistic Models
Contrast and Generation Make BART a Good Dialogue Emotion Recognizer
Contrast-Enhanced Semi-supervised Text Classification with Few Labels
Contrastive Instruction-Trajectory Learning for Vision-Language Navigation
Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-Supervised Action Recognition
Contrastive Personalization Approach to Suspect Identification (Student Abstract)
Contrastive Quantization with Code Memory for Unsupervised Image Retrieval
Contrastive Spatio-Temporal Pretext Learning for Self-Supervised Video Representation
ContrastNet: A Contrastive Learning Framework for Few-Shot Text Classification
Contribution-Aware Federated Learning for Smart Healthcare
Controlling the Spread of Two Secrets in Diverse Social Networks (Student Abstract)
Controlling Underestimation Bias in Reinforcement Learning via Quasi-median Operation
Control-Oriented Model-Based Reinforcement Learning with Implicit Differentiation
Convergence and Optimality of Policy Gradient Methods in Weakly Smooth Settings
Convolutional Neural Network Compression through Generalized Kronecker Product Decomposition
Cooperative Multi-Agent Fairness and Equivariant Policies
Coordinate Descent on the Orthogonal Group for Recurrent Neural Network Training
Coordinating Followers to Reach Better Equilibria: End-to-End Gradient Descent for Stackelberg Games
Coordinating Momenta for Cross-Silo Federated Learning
Co-promotion Predictions of Financing Market and Sales Market: A Cooperative-Competitive Attention Approach
Correlation Field for Boosting 3D Object Detection in Structured Scenes
Cosine Model Watermarking against Ensemble Distillation
Covered Information Disentanglement: Model Transparency via Unbiased Permutation Importance
COVID-EENet: Predicting Fine-Grained Impact of COVID-19 on Local Economies
CPRAL: Collaborative Panoptic-Regional Active Learning for Semantic Segmentation
CQA-Face: Contrastive Quality-Aware Attentions for Face Recognition
Creating Interactive Crowds with Reinforcement Learning
Creating Interpretable Data-Driven Approaches for Tropical Cyclones Forecasting
Creativity of AI: Automatic Symbolic Option Discovery for Facilitating Deep Reinforcement Learning
Criticality-Based Advice in Reinforcement Learning (Student Abstract)
Cross-Dataset Collaborative Learning for Semantic Segmentation in Autonomous Driving
Cross-Domain Collaborative Normalization via Structural Knowledge
Cross-Domain Empirical Risk Minimization for Unbiased Long-Tailed Classification
Cross-Domain Few-Shot Graph Classification
Cross-domain graph anomaly detection via anomaly-aware contrastive alignment
Cross-Lingual Adversarial Domain Adaptation for Novice Programming
Cross-Modal Coherence for Text-to-Image Retrieval
Cross-Modal Federated Human Activity Recognition via Modality-Agnostic and Modality-Specific Representation Learning

« prev Page 7/34 next »