Tackling the Imbalance for GNNs
This tackles the imbalance issue in GNNs, which is a domain-specific problem affecting graph-based learning tasks, but the approach is incremental as it builds on existing GNN frameworks.
The study addresses the class imbalance problem in graph neural networks (GNNs), which causes misclassification in minority classes and reduces overall performance, by proposing a node-level label difference index (LDI) and four new methods based on it, with three methods showing improved classification accuracies in transductive and inductive settings.
Different from deep neural networks for non-graph data classification, graph neural networks (GNNs) leverage the information exchange between nodes (or samples) when representing nodes. The category distribution shows an imbalance or even a highly-skewed trend on nearly all existing benchmark GNN data sets. The imbalanced distribution will cause misclassification of nodes in the minority classes, and even cause the classification performance on the entire data set to decrease. This study explores the effects of the imbalance problem on the performances of GNNs and proposes new methodologies to solve it. First, a node-level index, namely, the label difference index ($LDI$), is defined to quantitatively analyze the relationship between imbalance and misclassification. The less samples in a class, the higher the value of its average $LDI$; the higher the $LDI$ of a sample, the more likely the sample will be misclassified. We define a new loss and propose four new methods based on $LDI$. Experimental results indicate that the classification accuracies of the three among our proposed four new methods are better in both transductive and inductive settings. The $LDI$ can be applied to other GNNs.