Embedding of embedding (EOE) : Joint embedding for coupled heterogeneous networks

Linchuan Xu, Xiaokai Wei, Jiannong Cao, Philip S. Yu

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

84 Citations (Scopus)

Abstract

Network embedding is increasingly employed to assist net- work analysis as it is effective to learn latent features that en- code linkage information. Various network embedding meth- ods have been proposed, but they are only designed for a sin- gle network scenario. In the era of big data, different types of related information can be fused together to form a cou- pled heterogeneous network, which consists of two different but related sub-networks connected by inter-network edges. In this scenario, the inter-network edges can act as comple- mentary information in the presence of intra-network ones. This complementary information is important because it can make latent features more comprehensive and accurate. And it is more important when the intra-network edges are ab- sent, which can be referred to as the cold-start problem. In this paper, we thus propose a method named embedding of embedding (EOE) for coupled heterogeneous networks. In the EOE, latent features encode not only intra-network edges, but also inter-network ones. To tackle the challenge of heterogeneities of two networks, the EOE incorporates a harmonious embedding matrix to further embed the em- beddings that only encode intra-network edges. Empirical experiments on a variety of real-world datasets demonstrate the EOE outperforms consistently single network embedding methods in applications including visualization, link predic- tion multi-class classification, and multi-label classification.
Original languageEnglish
Title of host publicationWSDM 2017 - Proceedings of the 10th ACM International Conference on Web Search and Data Mining
PublisherAssociation for Computing Machinery, Inc
Pages741-749
Number of pages9
ISBN (Electronic)9781450346757
DOIs
Publication statusPublished - 2 Feb 2017
Event10th ACM International Conference on Web Search and Data Mining, WSDM 2017 - The Guildhall, Cambridge, United Kingdom
Duration: 6 Feb 201710 Feb 2017

Conference

Conference10th ACM International Conference on Web Search and Data Mining, WSDM 2017
Country/TerritoryUnited Kingdom
CityCambridge
Period6/02/1710/02/17

Keywords

  • Coupled heterogeneous networks
  • Data mining
  • Network embedding

ASJC Scopus subject areas

  • Computer Science Applications
  • Information Systems
  • Computer Networks and Communications
  • Software

Cite this