A Semantic-Rich Similarity Measure in Heterogeneous Information Networks

TL;DR

This paper introduces a new similarity measure called SMSS for heterogeneous information networks that automatically captures rich semantics and outperforms existing metrics in ranking and clustering tasks.

Contribution

The paper proposes a stratified meta structure based similarity measure that is automatically constructed and captures richer semantics than existing user-defined metrics.

Findings

SMSS outperforms state-of-the-art metrics in ranking tasks.

SMSS improves clustering performance.

The method automatically constructs stratified meta structures.

Abstract

Measuring the similarities between objects in information networks has fundamental importance in recommendation systems, clustering and web search. The existing metrics depend on the meta path or meta structure specified by users. In this paper, we propose a stratified meta structure based similarity $SMSS$ in heterogeneous information networks. The stratified meta structure can be constructed automatically and capture rich semantics. Then, we define the commuting matrix of the stratified meta structure by virtue of the commuting matrices of meta paths and meta structures. As a result, $SMSS$ is defined by virtue of these commuting matrices. Experimental evaluations show that the proposed $SMSS$ on the whole outperforms the state-of-the-art metrics in terms of ranking and clustering.