Rethinking Semi-Supervised Imbalanced Node Classification from Bias-Variance Decomposition
This addresses the problem of imbalanced node classification in graph neural networks, providing a novel theoretical perspective for researchers and practitioners in graph learning.
The paper tackled class imbalance in graph neural networks for node classification by linking imbalance to model variance through a bias-variance decomposition framework and using graph augmentation with regularization. It demonstrated state-of-the-art performance on multiple benchmarks in imbalanced scenarios.
This paper introduces a new approach to address the issue of class imbalance in graph neural networks (GNNs) for learning on graph-structured data. Our approach integrates imbalanced node classification and Bias-Variance Decomposition, establishing a theoretical framework that closely relates data imbalance to model variance. We also leverage graph augmentation technique to estimate the variance, and design a regularization term to alleviate the impact of imbalance. Exhaustive tests are conducted on multiple benchmarks, including naturally imbalanced datasets and public-split class-imbalanced datasets, demonstrating that our approach outperforms state-of-the-art methods in various imbalanced scenarios. This work provides a novel theoretical perspective for addressing the problem of imbalanced node classification in GNNs.