VIGraph: Self-supervised Learning for Class-Imbalanced Node Classification. (arXiv:2311.01191v1 [cs.LG])

Class imbalance in graph data poses significant challenges for node
classification. Existing methods, represented by SMOTE-based approaches,
partially alleviate this issue but still exhibit limitations during imbalanced
scenario construction. Self-supervised learning (SSL) offers a promising
solution by synthesizing minority nodes from the data itself, yet its potential
remains unexplored. In this paper, we analyze the limitations of SMOTE-based
approaches and introduce VIGraph, a novel SSL model based on the
self-supervised Variational Graph Auto-Encoder (VGAE) that leverages
Variational Inference (VI) to …

arxiv challenges classification construction data graph issue limitations node self-supervised learning smote solution ssl supervised learning