Readable contrast mining method for heterogeneous bipartite networks with class label

Mao Nishiguchi, Yasuyuki Shirai, Hiroyuki Morita, Yusuke Goto

Research output: Contribution to conferencePaperpeer-review

Abstract

Recent IoT trends have been driving usage of multi-source data. In general, since the multi-source data have different nature, we need to make heterogeneous networks to represent them simultaneously. This paper presents a novel mining method to discover factors that characterize differences between classes for heterogeneous bipartite networks. In order to find the differences from such the large-scale networks efficiently, it is important to use distributed representations that preserve first-order and second-order proximity between vertices of the networks. We propose an effective representation method for heterogeneous bipartite networks with class label. And we propose a readable visualization method for revealing the factors on the embedding space. From computational experiments using real-world data which include the multimedia access logs and the results of questionnaire for the users, we show that the proposed method can acquire distributed representations with higher explanatory power than existing methods, and can discover important factors.

Original languageEnglish
Publication statusPublished - 2020
Externally publishedYes
Event24th Pacific Asia Conference on Information Systems: Information Systems (IS) for the Future, PACIS 2020 - Dubai, United Arab Emirates
Duration: 2020 Jun 202020 Jun 24

Conference

Conference24th Pacific Asia Conference on Information Systems: Information Systems (IS) for the Future, PACIS 2020
Country/TerritoryUnited Arab Emirates
CityDubai
Period20/6/2020/6/24

Keywords

  • Contrast data mining
  • Heterogeneous bipartite network embedding
  • Multi-source data analysis

ASJC Scopus subject areas

  • Information Systems

Fingerprint

Dive into the research topics of 'Readable contrast mining method for heterogeneous bipartite networks with class label'. Together they form a unique fingerprint.

Cite this