Easing Embedding Learning By Comprehensive Transcription Of Heterogeneous Information Networks

Authors:
Yu Shi University of Illinois at Urbana-Champaign
Qi Zhu University of Illinois Urbana-Champaign
Fang Guo University of Illinois Urbana-Champaign
Chao Zhang University of Illinois Urbana-Champaign
Jiawei Han University of Illinois at Urbana-Champaign

Introduction:

the authors propose to study the problem of comprehensive transcription of heterogeneous information networks(HINs). To cope with the challenges in the comprehensive transcription of HINs, the authors propose the HEER algorithm, which embeds HINs via edge representations that are further coupled with properly-learned heterogeneous metrics.

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.

You may want to know: