Meta-GCN: A Dynamically Weighted Loss Minimization Method for Dealing with the Data Imbalance in Graph Neural Networks

TL;DR

Meta-GCN introduces a meta-learning approach to dynamically assign weights to training samples, effectively addressing class imbalance in graph neural networks and improving classification performance.

Contribution

It presents a novel meta-learning algorithm that adaptively learns sample weights by minimizing unbiased meta-data loss, outperforming existing methods.

Findings

Meta-GCN achieves higher accuracy than state-of-the-art methods.

It improves AUC-ROC and macro F1-Score on benchmark datasets.

The approach effectively mitigates class imbalance bias.

Abstract

Although many real-world applications, such as disease prediction, and fault detection suffer from class imbalance, most existing graph-based classification methods ignore the skewness of the distribution of classes; therefore, tend to be biased towards the majority class(es). Conventional methods typically tackle this problem through the assignment of weights to each one of the class samples based on a function of their loss, which can lead to over-fitting on outliers. In this paper, we propose a meta-learning algorithm, named Meta-GCN, for adaptively learning the example weights by simultaneously minimizing the unbiased meta-data set loss and optimizing the model weights through the use of a small unbiased meta-data set. Through experiments, we have shown that Meta-GCN outperforms state-of-the-art frameworks and other baselines in terms of accuracy, the area under the receiver operating characteristic (AUC-ROC) curve, and macro F1-Score for classification tasks on two different datasets.