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
Bi-volution: A Static and Dynamic Coupled Filter
Blindfolded Attackers Still Threatening: Strict Black-Box Adversarial Attacks on Graphs
Blocking Influence at Collective Level with Hard Constraints (Student Abstract)
Block Modeling-Guided Graph Convolutional Neural Networks
Block-Skim: Efficient Question Answering for Transformer
Blockwise Sequential Model Learning for Partially Observable Reinforcement Learning
BM-NAS: Bilevel Multimodal Neural Architecture Search
Boosting Active Learning via Improving Test Performance
Boosting Contrastive Learning with Relation Knowledge Distillation
Boosting Generative Zero-Shot Learning by Synthesizing Diverse Features with Attribute Augmentation
Boosting the Transferability of Video Adversarial Examples via Temporal Translation
Boost Supervised Pretraining for Visual Transfer Learning: Implications of Self-Supervised Contrastive Representation Learning
Bounding Quality in Diverse Planning
Bounds on Causal Effects and Application to High Dimensional Data
Braid: Weaving Symbolic and Neural Knowledge into Coherent Logical Explanations
Breaking the Convergence Barrier: Optimization via Fixed-Time Convergent Flows
Bridging between Cognitive Processing Signals and Linguistic Features via a Unified Attentional Network
Bridging LTLf Inference to GNN Inference for Learning LTLf Formulae
Bridging the Gap between Expression and Scene Text for Referring Expression Comprehension (Student Abstract)
Bridging the Gap: Using Deep Acoustic Representations to Learn Grounded Language from Percepts and Raw Speech
BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documents
BScNets: Block Simplicial Complex Neural Networks
Building Goal-Oriented Dialogue Systems with Situated Visual Context
C2L: Causally Contrastive Learning for Robust Text Classification
C3D and Localization Model for Locating and Recognizing the Actions from Untrimmed Videos (Student Abstract)
CADRE: A Cascade Deep Reinforcement Learning Framework for Vision-Based Autonomous Urban Driving
CAISE: Conversational Agent for Image Search and Editing
Calibrated Nonparametric Scan Statistics for Anomalous Pattern Detection in Graphs
CALIP: Zero-Shot Enhancement of CLIP with Parameter-Free Attention
Call for Customized Conversation: Customized Conversation Grounding Persona and Knowledge
Can Machines Read Coding Manuals Yet? - A Benchmark for Building Better Language Models for Code Understanding
Can Semantic Labels Assist Self-Supervised Visual Representation Learning?
Can Vision Transformers Learn without Natural Images?
Capsule Graph Neural Network for Multi-Label Image Recognition (Student Abstract)
Categorical Neighbour Correlation Coefficient (CnCor) for Detecting Relationships between Categorical Variables
Category-Specific Nuance Exploration Network for Fine-Grained Object Retrieval
CATN: Cross Attentive Tree-Aware Network for Multivariate Time Series Forecasting
Causal Discovery in Hawkes Processes by Minimum Description Length
CausalGNN: Causal-Based Graph Neural Networks for Spatio-Temporal Epidemic Forecasting
Causal Intervention for Subject-Deconfounded Facial Action Unit Recognition
CB+NN Ensemble to Improve Tracking Accuracy in Air Surveillance
CCA: An ML Pipeline for Cloud Anomaly Troubleshooting
CC-CERT: A Probabilistic Approach to Certify General Robustness of Neural Networks
CEM: Commonsense-Aware Empathetic Response Generation
Certified Robustness of Nearest Neighbors against Data Poisoning and Backdoor Attacks
Certified Symmetry and Dominance Breaking for Combinatorial Optimisation
CF-DETR: Coarse-to-Fine Transformers for End-to-End Object Detection
Chaining Value Functions for Off-Policy Learning
Channelized Axial Attention - considering Channel Relation within Spatial Attention for Semantic Segmentation
Characterization of Incentive Compatibility of an Ex-ante Constrained Player

« prev Page 5/34 next »