Imbalanced Node Processing Method in Graph Neural Network Classification Task

TL;DR

This paper addresses class imbalance in graph neural network node classification by introducing GHMC Loss, which improves accuracy by 3% on benchmarks by effectively handling difficult and marginal samples.

Contribution

The paper proposes integrating GHMC Loss into GNNs to better manage class imbalance, enhancing classification accuracy over traditional loss functions.

Findings

Improved accuracy by 3% on benchmark datasets.

Effective handling of difficult and marginal samples.

Addresses class imbalance in GNN node classification.

Abstract

In recent years, the node classification task in graph neural networks(GNNs) has developed rapidly, driving the development of research in various fields. However, there are a large number of class imbalances in the graph data, and there is a large gap between the number of different classes, resulting in suboptimal results in classification. Proposing a solution to the imbalance problem has become indispensable for the successful advancement of our downstream missions. Therefore, we start with the loss function and try to find a loss function that can effectively solve the imbalance of graph nodes to participate in the node classification task. thence, we introduce GHMC Loss into the graph neural networks to deal with difficult samples that are not marginal. Attenuate the loss contribution of marginal samples and simple samples. Experiments on multiple benchmarks show that our method can effectively deal with the class imbalance problem, and our method improves the accuracy by 3% compared to the traditional loss function.