GraphDIVE: Graph Classification by Mixture of Diverse Experts

GraphDIVE: Graph Classification by Mixture of Diverse Experts

Fenyu Hu, Liping Wang, Qiang Liu, Shu Wu, Liang Wang, Tieniu Tan

Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence
Main Track. Pages 2080-2086. https://doi.org/10.24963/ijcai.2022/289

Graph classification is a challenging research task in many applications across a broad range of domains. Recently, Graph Neural Network (GNN) models have achieved superior performance on various real-world graph datasets. Despite their successes, most of current GNN models largely suffer from the ubiquitous class imbalance problem, which typically results in prediction bias towards majority classes. Although many imbalanced learning methods have been proposed, they mainly focus on regular Euclidean data and cannot well utilize topological structure of graph (non-Euclidean) data. To boost the performance of GNNs and investigate the relationship between topological structure and class imbalance, we propose GraphDIVE, which learns multi-view graph representations and combine multi-view experts (i.e., classifiers). Specifically, multi-view graph representations correspond to the intrinsic diverse graph topological structure characteristics. Extensive experiments on molecular benchmark datasets demonstrate the effectiveness of the proposed approach.
Keywords:
Data Mining: Mining Graphs
Machine Learning: Sequence and Graph Learning