Relation Structure-Aware Heterogeneous Information Network Embedding

TL;DR

This paper introduces RHINE, a relation structure-aware embedding model for heterogeneous information networks that distinguishes relation types to improve embedding quality, outperforming existing methods in multiple tasks.

Contribution

The paper proposes a novel approach that categorizes relations into two types and develops tailored models for each, enhancing the representation of heterogeneous networks.

Findings

RHINE outperforms state-of-the-art methods in node clustering.

RHINE achieves superior results in link prediction.

RHINE improves node classification accuracy.

Abstract

Heterogeneous information network (HIN) embedding aims to embed multiple types of nodes into a low-dimensional space. Although most existing HIN embedding methods consider heterogeneous relations in HINs, they usually employ one single model for all relations without distinction, which inevitably restricts the capability of network embedding. In this paper, we take the structural characteristics of heterogeneous relations into consideration and propose a novel Relation structure-aware Heterogeneous Information Network Embedding model (RHINE). By exploring the real-world networks with thorough mathematical analysis, we present two structure-related measures which can consistently distinguish heterogeneous relations into two categories: Affiliation Relations (ARs) and Interaction Relations (IRs). To respect the distinctive characteristics of relations, in our RHINE, we propose different models specifically tailored to handle ARs and IRs, which can better capture the structures and semantics of the networks. At last, we combine and optimize these models in a unified and elegant manner. Extensive experiments on three real-world datasets demonstrate that our model significantly outperforms the state-of-the-art methods in various tasks, including node clustering, link prediction, and node classification.