Learning graph representation via frequent subgraphs

Dang Nguyen, Wei Luo, Tu Dinh Nguyen, Svetha Venkatesh, Dinh Phung

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

11 Citations (Scopus)

Abstract

We propose a novel approach to learn distributed representation for graph data. Our idea is to combine a recently introduced neural document embedding model with a traditional pattern mining technique, by treating a graph as a document and frequent subgraphs as atomic units for the embedding process. Compared to the latest graph embedding methods, our proposed method offers three key advantages: fully unsupervised learning, entire-graph embedding, and edge label leveraging. We demonstrate our method on several datasets in comparison with a comprehensive list of up-to-date stateof-the-art baselines where we show its advantages for both classification and clustering tasks.

Original languageEnglish
Title of host publication2018 SIAM International Conference on Data Mining, May 3-5, 2018
Subtitle of host publicationSan Diego Marriott Mission Valley, San Diego, California, USA
EditorsMartin Ester, Dino Pedreschi
Place of PublicationPhiladelphia PA USA
PublisherSociety for Industrial & Applied Mathematics (SIAM)
Pages306-314
Number of pages9
ISBN (Print)9781611975321
DOIs
Publication statusPublished - 2018
Externally publishedYes
EventSIAM International Conference on Data Mining 2018 - San Diego Marriott Mission Valley, San Diego, United States of America
Duration: 3 May 20185 May 2018
https://epubs.siam.org/doi/10.1137/1.9781611975321.fm

Conference

ConferenceSIAM International Conference on Data Mining 2018
Abbreviated titleSDM 18
CountryUnited States of America
CitySan Diego
Period3/05/185/05/18
Internet address

Cite this