Class-Imbalanced Graph Learning without Class Rebalancing
Zhining Liu, Ruizhong Qiu, Zhichen Zeng, Hyunsik Yoo, David Zhou, Zhe Xu, Yada Zhu, Kommy Weldemariam
Abstract
Class imbalance is prevalent in real-world node classification tasks and poses great challenges for graph learning models. Most existing studies are rooted in a class-rebalancing (CR) perspective and address class imbalance with class-wise reweighting or resampling. In this work, we approach the root cause of class-imbalance bias from an topological paradigm. Specifically, we theoretically reveal two **fundamental phenomena in the graph topology** that greatly exacerbate the predictive bias stemming from class imbalance. On this basis, we devise a lightweight topological augmentation framework BAT to mitigate the class-imbalance bias without class rebalancing. Being orthogonal to CR, BAT can function as an **efficient plug-and-play module** that can be seamlessly combined with and significantly boost existing CR techniques. Systematic experiments on real-world imbalanced graph learning tasks show that BAT can deliver up to 46.27% performance gain and up to 72.74% bias reduction over existing techniques. Code, examples, and documentations are available at https://github.com/ZhiningLiu1998/BAT.
BibTeX
@inproceedings{
liu2024classimbalanced,
title={Class-Imbalanced Graph Learning without Class Rebalancing},
author={Zhining Liu and Ruizhong Qiu and Zhichen Zeng and Hyunsik Yoo and David Zhou and Zhe Xu and Yada Zhu and Kommy Weldemariam and Jingrui He and Hanghang Tong},
booktitle={Forty-first International Conference on Machine Learning},
year={2024},
url={https://openreview.net/forum?id=pPnkpvBeZN}
}