Semi-Supervised Hierarchical Graph Classification

TL;DR

This paper introduces SEAL-CI, a semi-supervised method for hierarchical graph classification where nodes are graph instances, leveraging hierarchical mutual information to improve classification in domains like social and biological networks.

Contribution

The paper proposes a novel semi-supervised approach, SEAL-CI, with a hierarchical mutual information measure for effective classification of graph-structured data where nodes are graphs.

Findings

SEAL-CI outperforms baseline methods on social and text network datasets.

Hierarchical mutual information improves consistency across graph levels.

Theoretical guarantees support the HGMI computation.

Abstract

Node classification and graph classification are two graph learning problems that predict the class label of a node and the class label of a graph respectively. A node of a graph usually represents a real-world entity, e.g., a user in a social network, or a document in a document citation network. In this work, we consider a more challenging but practically useful setting, in which a node itself is a graph instance. This leads to a hierarchical graph perspective which arises in many domains such as social network, biological network and document collection. We study the node classification problem in the hierarchical graph where a 'node' is a graph instance. As labels are usually limited, we design a novel semi-supervised solution named SEAL-CI. SEAL-CI adopts an iterative framework that takes turns to update two modules, one working at the graph instance level and the other at the hierarchical graph level. To enforce a consistency among different levels of hierarchical graph, we propose the Hierarchical Graph Mutual Information (HGMI) and further present a way to compute HGMI with theoretical guarantee. We demonstrate the effectiveness of this hierarchical graph modeling and the proposed SEAL-CI method on text and social network data.