Imbalanced Graph Classification with Multi-scale Oversampling Graph Neural Networks

arXiv:2405.04903v1 Announce Type: new
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 …

abstract arxiv challenge classification cs.lg enabling functions graph graph neural networks graph representation graphs learn loss networks neural networks oversampling representation representation learning scale type