Unsupervised Hierarchical Graph Representation Learning by Mutual Information Maximization
This addresses the need for explainable and label-free graph learning in domains like social networks or bioinformatics, though it is incremental as it builds on existing GNN frameworks.
The paper tackles the problem of graph representation learning by proposing an unsupervised method that generates hierarchical representations through mutual information maximization, achieving comparable results to state-of-the-art supervised methods on node and graph classification benchmarks.
Graph representation learning based on graph neural networks (GNNs) can greatly improve the performance of downstream tasks, such as node and graph classification. However, the general GNN models do not aggregate node information in a hierarchical manner, and can miss key higher-order structural features of many graphs. The hierarchical aggregation also enables the graph representations to be explainable. In addition, supervised graph representation learning requires labeled data, which is expensive and error-prone. To address these issues, we present an unsupervised graph representation learning method, Unsupervised Hierarchical Graph Representation (UHGR), which can generate hierarchical representations of graphs. Our method focuses on maximizing mutual information between "local" and high-level "global" representations, which enables us to learn the node embeddings and graph embeddings without any labeled data. To demonstrate the effectiveness of the proposed method, we perform the node and graph classification using the learned node and graph embeddings. The results show that the proposed method achieves comparable results to state-of-the-art supervised methods on several benchmarks. In addition, our visualization of hierarchical representations indicates that our method can capture meaningful and interpretable clusters.