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
Attention-Aligned Transformer for Image Captioning
Attention-Based Transformation from Latent Features to Point Clouds
Attention Biasing and Context Augmentation for Zero-Shot Control of Encoder-Decoder Transformers for Natural Language Generation
Attribute-Based Progressive Fusion Network for RGBT Tracking
AUC Maximization for Low-Resource Named Entity Recognition
Augmentation-Free Self-Supervised Learning on Graphs
Augmentation of Chinese Character Representations with Compositional Graph Learning (Student Abstract)
A Unified Framework for Real Time Motion Completion
A Unifying Theory of Thompson Sampling for Continuous Risk-Averse Bandits
Authentic Integration of Ethics and AI through Sociotechnical, Problem-Based Learning
AutoBERT-Zero: Evolving BERT Backbone from Scratch
AutoCFR: Learning to Design Counterfactual Regret Minimization Algorithms
AutoGCL: Automated Graph Contrastive Learning via Learnable View Generators
Automated Synthesis of Generalized Invariant Strategies via Counterexample-Guided Strategy Refinement
Automatic Slides Generation for Scholarly Papers: A Fine-Grained Dataset and Baselines (Student Abstract)
A Variant of Concurrent Constraint Programming on GPU
Axiomatization of Aggregates in Answer Set Programming
AXM-Net: Implicit Cross-Modal Feature Alignment for Person Re-identification
BabelNet Meaning Representation: A Fully Semantic Formalism to Overcome Language Barriers
Backdoor Attacks on the DNN Interpretation System
Backprop-Free Reinforcement Learning with Active Neural Generative Coding
Bag Graph: Multiple Instance Learning Using Bayesian Graph Neural Networks
Balanced Self-Paced Learning for AUC Maximization
Balancing the Spread of Two Opinions in Sparse Social Networks (Student Abstract)
Bandit Data-Driven Optimization for Crowdsourcing Food Rescue Platforms
Bandit Limited Discrepancy Search and Application to Machine Learning Pipeline Optimization
Barely-Supervised Learning: Semi-supervised Learning with Very Few Labeled Images
Batch Active Learning with Graph Neural Networks via Multi-Agent Deep Reinforcement Learning
Batch Normalization Is Blind to the First and Second Derivatives of the Loss
BATUDE: Budget-Aware Neural Network Compression Based on Tucker Decomposition
Bayesian Model-Based Offline Reinforcement Learning for Product Allocation
Bayesian Optimisation for Active Monitoring of Air Pollution
Bayesian Optimization-Based Combinatorial Assignment
Bayesian Persuasion in Sequential Decision-Making
'Beach' to 'Bitch': Inadvertent Unsafe Transcription of Kids' Content on YouTube
Behind the Curtain: Learning Occluded Shapes for 3D Object Detection
Being Friends Instead of Adversaries: Deep Networks Learn from Data Simplified by Other Networks
BERTMap: A BERT-Based Ontology Alignment System
Best-Buddy GANs for Highly Detailed Image Super-resolution
Better Parameter-Free Stochastic Optimization with ODE Updates for Coin-Betting
Beyond GNNs: An Efficient Architecture for Graph Problems
Beyond Grounding: Extracting Fine-Grained Event Hierarchies across Modalities
Beyond Learning Features: Training a Fully-Functional Classifier with ZERO Instance-Level Labels
Beyond NaN: Resiliency of Optimization Layers in the Face of Infeasibility
Beyond Shared Subspace: A View-Specific Fusion for Multi-View Multi-Label Learning
Beyond Smoothing: Unsupervised Graph Representation Learning with Edge Heterophily Discriminating
Bi-CMR: Bidirectional Reinforcement Guided Hashing for Effective Cross-Modal Retrieval
Bidding Graph Games with Partially-Observable Budgets
BigCQ: Generating a Synthetic Set of Competency Questions Formalized into SPARQL-OWL (Student Abstract)
BiRdQA: A Bilingual Dataset for Question Answering on Tricky Riddles

« prev Page 4/34 next »