Graph Classification by Mixture of Diverse Experts
This addresses imbalanced graph classification for applications across various domains, but it is incremental as it adapts existing mixture-of-experts methods to a specific bottleneck.
The paper tackles the problem of imbalanced class distribution in graph classification, which causes prediction bias towards majority classes, by proposing GraphDIVE, a framework using a mixture of diverse experts to partition and train on subsets, and demonstrates its effectiveness on real-world datasets.
Graph classification is a challenging research problem in many applications across a broad range of domains. In these applications, it is very common that class distribution is imbalanced. Recently, Graph Neural Network (GNN) models have achieved superior performance on various real-world datasets. Despite their success, most of current GNN models largely overlook the important setting of imbalanced class distribution, which typically results in prediction bias towards majority classes. To alleviate the prediction bias, we propose to leverage semantic structure of dataset based on the distribution of node embedding. Specifically, we present GraphDIVE, a general framework leveraging mixture of diverse experts (i.e., graph classifiers) for imbalanced graph classification. With a divide-and-conquer principle, GraphDIVE employs a gating network to partition an imbalanced graph dataset into several subsets. Then each expert network is trained based on its corresponding subset. Experiments on real-world imbalanced graph datasets demonstrate the effectiveness of GraphDIVE.