Graph Attention Network
Graph Attention Networks (GATs) are a type of graph neural network designed to learn relationships within graph-structured data by assigning attention weights to different nodes based on their relevance to a given task. Current research focuses on improving GAT performance in various applications, including developing more sophisticated attention mechanisms, addressing limitations in handling heterophilic graphs and long-range dependencies, and integrating GATs with other techniques like transformers and multi-modal data fusion. This work has significant implications across diverse fields, enabling advancements in areas such as drug discovery, financial modeling, image analysis, and social network analysis through improved data representation and predictive modeling.
Papers
An Explainable Geometric-Weighted Graph Attention Network for Identifying Functional Networks Associated with Gait Impairment
Favour Nerrise, Qingyu Zhao, Kathleen L. Poston, Kilian M. Pohl, Ehsan Adeli
Compact & Capable: Harnessing Graph Neural Networks and Edge Convolution for Medical Image Classification
Aryan Singh, Pepijn Van de Ven, Ciarán Eising, Patrick Denny
Optimization and Interpretability of Graph Attention Networks for Small Sparse Graph Structures in Automotive Applications
Marion Neumeier, Andreas Tollkühn, Sebastian Dorn, Michael Botsch, Wolfgang Utschick
Demystifying Oversmoothing in Attention-Based Graph Neural Networks
Xinyi Wu, Amir Ajorlou, Zihui Wu, Ali Jadbabaie