VIGraph: Generative Self-supervised Learning for Class-Imbalanced Node Classification

arXiv:2311.01191v2 Announce Type: replace
Abstract: Class imbalance in graph data presents significant challenges for node classification. While existing methods, such as SMOTE-based approaches, partially mitigate this issue, they still exhibit limitations in constructing imbalanced graphs. Generative self-supervised learning (SSL) methods, exemplified by graph autoencoders (GAEs), offer a promising solution by directly generating minority nodes from the data itself, yet their potential remains underexplored. In this paper, we delve into the shortcomings of SMOTE-based approaches in the construction of imbalanced graphs. …

abstract arxiv autoencoders challenges class classification cs.ai cs.lg data generative graph graph data graphs issue limitations node self-supervised learning smote solution ssl supervised learning type