Semi-Supervised Hierarchical Graph Classification

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.

Accepted by TPAMI. Journal extension of arXiv:1904.05003

References in corpus (6)

• graph2vec: Learning Distributed Representations of Graphs
• Contrastive Multi-View Representation Learning on Graphs
• Self-Attention Graph Pooling
• An Overview of Deep Semi-Supervised Learning
• Rethinking Graph Neural Networks for Anomaly Detection
• Graph Autoencoders with Deconvolutional Networks

Cited by in corpus (6)

• A Comprehensive Survey on Deep Graph Representation Learning
• Current and future directions in network biology
• GALA: Graph Diffusion-based Alignment with Jigsaw for Source-free Domain Adaptation
• Path-based Explanation for Knowledge Graph Completion
• Towards Lightweight Graph Neural Network Search with Curriculum Graph Sparsification
• Separated Contrastive Learning for Matching in Cross-domain Recommendation with Curriculum Scheduling