Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

9-2024

Abstract

One main challenge in imbalanced graph classification is to learn expressive representations of the graphs in under-represented (minority) classes. Existing generic imbalanced learning methods, such as oversampling and imbalanced learning loss functions, can be adopted for enabling graph representation learning models to cope with this challenge. However, these methods often directly operate on the graph representations, ignoring rich discriminative information within the graphs and their interactions. To tackle this issue, we introduce a novel multi-scale oversampling graph neural network (MOSGNN) that learns expressive minority graph representations based on intra- and inter-graph semantics resulting from oversampled graphs at multiple scales - subgraph, graph, and pairwise graphs. It achieves this by jointly optimizing subgraph-level, graph-level, and pairwise-graph learning tasks to learn the discriminative information embedded within and between the minority graphs. Extensive experiments on 16 imbalanced graph datasets show that MOSGNN i) significantly outperforms five state-of-the-art models, and ii) offers a generic framework, in which different advanced imbalanced learning loss functions can be easily plugged in and obtain significantly improved classification performance.

Keywords

Graph classification, Imbalanced learning, Oversampling, Graph neural networks

Discipline

Computer Sciences | Graphics and Human Computer Interfaces

Research Areas

Intelligent Systems and Optimization

Publication

Proceedings of the International Joint Conference on Neural Networks (IJCNN 2024) : Yokohama, Japan, June 30 - July 5

Identifier

10.1109/IJCNN60899.2024.10651097

Publisher

IEEE

City or Country

Yokohama, Japan

Additional URL

https://doi.org/10.1109/IJCNN60899.2024.10651097

Download

Share

COinS