Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

5-2023

Abstract

On graph data, the multitude of node or edge types gives rise to heterogeneous information networks (HINs). To preserve the heterogeneous semantics on HINs, the rich node/edge types become a cornerstone of HIN representation learning. However, in real-world scenarios, type information is often noisy, missing or inaccessible. Assuming no type information is given, we define a so-called latent heterogeneous graph (LHG), which carries latent heterogeneous semantics as the node/edge types cannot be observed. In this paper, we study the challenging and unexplored problem of link prediction on an LHG. As existing approaches depend heavily on type-based information, they are suboptimal or even inapplicable on LHGs. To address the absence of type information, we propose a model named LHGNN, based on the novel idea of semantic embedding at node and path levels, to capture latent semantics on and between nodes. We further design a personalization function to modulate the heterogeneous contexts conditioned on their latent semantics w.r.t. the target node, to enable finer-grained aggregation. Finally, we conduct extensive experiments on four benchmark datasets, and demonstrate the superior performance of LHGNN.

Keywords

Latent heterogeneous graph, Link prediction, Graph neural networks

Discipline

Databases and Information Systems | OS and Networks

Publication

Proceedings of the World Wide Web Conference, WWW 2023, Austin TX, USA, April 30 - May 4

First Page

263

Last Page

273

ISBN

978145039416-1

Identifier

10.1145/3543507.3583284

Publisher

ACM

City or Country

New York, USA

Download

Share

COinS