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
PrivateSNN: Privacy-Preserving Spiking Neural Networks
Probabilities Are Not Enough: Formal Controller Synthesis for Stochastic Dynamical Models with Epistemic Uncertainty
Probing Linguistic Information for Logical Inference in Pre-trained Language Models
Probing Word Syntactic Representations in the Brain by a Feature Elimination Method
Procedural Text Understanding via Scene-Wise Evolution
Procrastinated Tree Search: Black-Box Optimization with Delayed, Noisy, and Multi-Fidelity Feedback
Programmatic Modeling and Generation of Real-Time Strategic Soccer Environments for Reinforcement Learning
Programmatic Reward Design by Example
ProgressiveMotionSeg: Mutually Reinforced Framework for Event-Based Motion Segmentation
Progressive Multi-View Human Mesh Recovery with Self-Supervision
Promoting Single-Modal Optical Flow Network for Diverse Cross-Modal Flow Estimation
Proof of Learning: Towards a Practical Blockchain Consensus Mechanism Using Directed Guiding Gradients (Student Abstract)
Proportional Public Decisions
Propositional Encodings of Acyclicity and Reachability by Using Vertex Elimination
Protecting Intellectual Property of Language Generation APIs with Lexical Watermark
ProtGNN: Towards Self-Explaining Graph Neural Networks
Prototype-Based Explanations for Graph Neural Networks (Student Abstract)
Provable Guarantees for Understanding Out-of-Distribution Detection
Provable Sensor Sets for Epidemic Detection over Networks with Minimum Delay
Provably Efficient Causal Model-Based Reinforcement Learning for Systematic Generalization
Proximal PanNet: A Model-Based Deep Network for Pansharpening
Proxy Learning of Visual Concepts of Fine Art Paintings from Styles through Language Models
Prune and Tune Ensembles: Low-Cost Ensemble Learning with Sparse Independent Subnetworks
PUMA: Performance Unchanged Model Augmentation for Training Data Removal
PureGaze: Purifying Gaze Feature for Generalizable Gaze Estimation
Pushing the Limits of Rule Reasoning in Transformers through Natural Language Satisfiability
PYLON: A PyTorch Framework for Learning with Constraints
Q-Ball: Modeling Basketball Games Using Deep Reinforcement Learning
Qubit Routing Using Graph Neural Network Aided Monte Carlo Tree Search
QueryProp: Object Query Propagation for High-Performance Video Object Detection
QUILT: Effective Multi-Class Classification on Quantum Computers Using an Ensemble of Diverse Quantum Classifiers
Random Mapping Method for Large-Scale Terrain Modeling
Random Tensor Theory for Tensor Decomposition
Random vs. Best-First: Impact of Sampling Strategies on Decision Making in Model-Based Diagnosis
Ranking Info Noise Contrastive Estimation: Boosting Contrastive Learning via Ranked Positives
RareGAN: Generating Samples for Rare Classes
Real-Time Driver-Request Assignment in Ridesourcing
Reasoning about Causal Models with Infinitely Many Variables
Reconfiguring Shortest Paths in Graphs
Recovering the Propensity Score from Biased Positive Unlabeled Data
Recurrent Neural Network Controllers Synthesis with Stability Guarantees for Partially Observed Systems
Recursive Reasoning Graph for Multi-Agent Reinforcement Learning
Reducing Catastrophic Forgetting in Self Organizing Maps with Internally-Induced Generative Replay (Student Abstract)
Reducing Energy Consumption of Pressure Sensor Calibration Using Polynomial HyperNetworks with Fourier Features
Reducing Flipping Errors in Deep Neural Networks
Reference-Based Speech Enhancement via Feature Alignment and Fusion Network
Reference-Guided Pseudo-Label Generation for Medical Semantic Segmentation
ReforesTree: A Dataset for Estimating Tropical Forest Carbon Stock with Deep Learning and Aerial Imagery
Reforming an Envy-Free Matching
Regularization Guarantees Generalization in Bayesian Reinforcement Learning through Algorithmic Stability

« prev Page 25/34 next »