Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

11-2021

Abstract

While graph neural networks (GNNs) emerge as the state-of-the-art representation learning methods on graphs, they often require a large amount of labeled data to achieve satisfactory performance, which is often expensive or unavailable. To relieve the label scarcity issue, some pre-training strategies have been devised for GNNs, to learn transferable knowledge from the universal structural properties of the graph. However, existing pre-training strategies are only designed for homogeneous graphs, in which each node and edge belongs to the same type. In contrast, a heterogeneous graph embodies rich semantics, as multiple types of nodes interact with each other via different kinds of edges, which are neglected by existing strategies. In this paper, we propose a novel Contrastive Pre-Training strategy of GNNs on Heterogeneous Graphs (CPT-HG), to capture both the semantic and structural properties in a self-supervised manner. Specifically, we design semantic-aware pre-training tasks at both the relation- and subgraph-levels, and further enhance their representativeness by employing contrastive learning. We conduct extensive experiments on three real-world heterogeneous graphs, and promising results demonstrate the superior ability of our CPT-HG to transfer knowledge to various downstream tasks via pre-training.

Keywords

Pre-training, Heterogeneous graph, Self-supervised learning

Discipline

Databases and Information Systems

Research Areas

Data Science and Engineering

Publication

CIKM '21: Proceedings of the 30th ACM International Conference on Information and Knowledge Management, Virtual, November 1-5

First Page

803

Last Page

812

ISBN

9781450384469

Identifier

10.1145/3459637.3482332

Publisher

ACM

City or Country

New York

Additional URL

https://doi.org/10.1145/3459637.3482332

Share

COinS