Easing Embedding Learning by Comprehensive Transcription of Heterogeneous Information Networks

TL;DR

This paper introduces HEER, a novel embedding method for heterogeneous information networks that captures rich and incompatible semantics through comprehensive transcription, improving network understanding without extra supervision.

Contribution

The paper proposes HEER, a new HIN embedding algorithm using edge representations and heterogeneous metrics, enabling effective comprehensive transcription of HINs.

Findings

HEER outperforms existing methods on large-scale datasets.

Edge representations and heterogeneous metrics enhance embedding quality.

Experimental results validate the effectiveness of HEER.

Abstract

Heterogeneous information networks (HINs) are ubiquitous in real-world applications. In the meantime, network embedding has emerged as a convenient tool to mine and learn from networked data. As a result, it is of interest to develop HIN embedding methods. However, the heterogeneity in HINs introduces not only rich information but also potentially incompatible semantics, which poses special challenges to embedding learning in HINs. With the intention to preserve the rich yet potentially incompatible information in HIN embedding, we propose to study the problem of comprehensive transcription of heterogeneous information networks. The comprehensive transcription of HINs also provides an easy-to-use approach to unleash the power of HINs, since it requires no additional supervision, expertise, or feature engineering. To cope with the challenges in the comprehensive transcription of HINs, we propose the HEER algorithm, which embeds HINs via edge representations that are further coupled with properly-learned heterogeneous metrics. To corroborate the efficacy of HEER, we conducted experiments on two large-scale real-words datasets with an edge reconstruction task and multiple case studies. Experiment results demonstrate the effectiveness of the proposed HEER model and the utility of edge representations and heterogeneous metrics. The code and data are available at https://github.com/GentleZhu/HEER.