Graph Classification
Graph classification aims to automatically categorize graphs based on their structural and/or attribute properties, a crucial task with applications across diverse fields. Current research focuses on improving the efficiency and accuracy of graph neural networks (GNNs) for this purpose, exploring novel architectures like those incorporating attention mechanisms, hierarchical pooling, and disentangled representation learning, as well as developing techniques to address challenges such as oversmoothing, imbalanced datasets, and out-of-distribution generalization. These advancements are significant because they enable more effective analysis of complex relational data in domains ranging from social networks and bioinformatics to high-energy physics.
Papers
Enhancing High-Energy Particle Physics Collision Analysis through Graph Data Attribution Techniques
A. Verdone, A. Devoto, C. Sebastiani, J. Carmignani, M. D'Onofrio, S. Giagu, S. Scardapane, M. Panella
Data Augmentation in Graph Neural Networks: The Role of Generated Synthetic Graphs
Sumeyye Bas, Kiymet Kaya, Resul Tugay, Sule Gunduz Oguducu
Tackling Oversmoothing in GNN via Graph Sparsification: A Truss-based Approach
Tanvir Hossain, Khaled Mohammed Saifuddin, Muhammad Ifte Khairul Islam, Farhan Tanvir, Esra Akbas
Graph Structure Prompt Learning: A Novel Methodology to Improve Performance of Graph Neural Networks
Zhenhua Huang, Kunhao Li, Shaojie Wang, Zhaohong Jia, Wentao Zhu, Sharad Mehrotra
Unveiling Global Interactive Patterns across Graphs: Towards Interpretable Graph Neural Networks
Yuwen Wang, Shunyu Liu, Tongya Zheng, Kaixuan Chen, Mingli Song
Core Knowledge Learning Framework for Graph Adaptation and Scalability Learning
Bowen Zhang, Zhichao Huang, Genan Dai, Guangning Xu, Xiaomao Fan, Hu Huang