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
Understanding Enthymemes in Deductive Argumentation Using Semantic Distance Measures
Understanding Stochastic Optimization Behavior at the Layer Update Level (Student Abstract)
Underwater Ranker: Learn Which Is Better and How to Be Better
Unified Named Entity Recognition as Word-Word Relation Classification
Unifying Knowledge Base Completion with PU Learning to Mitigate the Observation Bias
Unifying Model Explainability and Robustness for Joint Text Classification and Rationale Extraction
UniMS: A Unified Framework for Multimodal Summarization with Knowledge Distillation
UNISON: Unpaired Cross-Lingual Image Captioning
Unit Selection with Causal Diagram
Universal and Tight Online Algorithms for Generalized-Mean Welfare
Unmasking the Mask - Evaluating Social Biases in Masked Language Models
Un-mix: Rethinking Image Mixtures for Unsupervised Visual Representation Learning
Unpaired Multi-Domain Stain Transfer for Kidney Histopathological Images
Unsupervised Adversarially Robust Representation Learning on Graphs
Unsupervised Anomaly Detection by Robust Density Estimation
Unsupervised Causal Binary Concepts Discovery with VAE for Black-Box Model Explanation
Unsupervised Coherent Video Cartoonization with Perceptual Motion Consistency
Unsupervised Deep Keyphrase Generation
Unsupervised Domain Adaptive Salient Object Detection through Uncertainty-Aware Pseudo-Label Learning
Unsupervised Editing for Counterfactual Stories
Unsupervised Identification of Materials with Hyperspectral Images
Unsupervised Learning of Compositional Scene Representations from Multiple Unspecified Viewpoints
Unsupervised Reinforcement Learning in Multiple Environments
Unsupervised Representation for Semantic Segmentation by Implicit Cycle-Attention Contrastive Learning
Unsupervised Sentence Representation via Contrastive Learning with Mixing Negatives
Unsupervised Temporal Video Grounding with Deep Semantic Clustering
Unsupervised Underwater Image Restoration: From a Homology Perspective
Up to 100x Faster Data-Free Knowledge Distillation
Using Conditional Independence for Belief Revision
Using Graph-Aware Reinforcement Learning to Identify Winning Strategies in Diplomacy Games (Student Abstract)
Using MaxSAT for Efficient Explanations of Tree Ensembles
Using Multimodal Data and AI to Dynamically Map Flood Risk
Using Public Data to Predict Demand for Mobile Health Clinics
Using Random Perturbations to Mitigate Adversarial Attacks on NLP Models
Using Reinforcement Learning for Operating Educational Campuses Safely during a Pandemic (Student Abstract)
Using Sampling to Estimate and Improve Performance of Automated Scoring Systems with Guarantees
VACA: Designing Variational Graph Autoencoders for Causal Queries
ValueNet: A New Dataset for Human Value Driven Dialogue System
VAST: The Valence-Assessing Semantics Test for Contextualizing Language Models
VECA: A New Benchmark and Toolkit for General Cognitive Development
VeNAS: Versatile Negotiating Agent Strategy via Deep Reinforcement Learning (Student Abstract)
Verification of Neural-Network Control Systems by Integrating Taylor Models and Zonotopes
Video as Conditional Graph Hierarchy for Multi-Granular Question Answering
VIDM: Video Implicit Diffusion Models
Vision Transformers Are Robust Learners
Visual Consensus Modeling for Video-Text Retrieval
Visual Definition Modeling: Challenging Vision & Language Models to Define Words and Objects
Visual Explanations for Convolutional Neural Networks via Latent Traversal of Generative Adversarial Networks (Student Abstract)
Visual Semantics Allow for Textual Reasoning Better in Scene Text Recognition
Visual Sound Localization in the Wild by Cross-Modal Interference Erasing

« prev Page 33/34 next »