Learning graph representation via frequent subgraphs

Nguyen, Dang Pham Hai, Luo, Wei, Nguyen, Tu Dinh, Venkatesh, Svetha and Phung, Quoc-Dinh 2018, Learning graph representation via frequent subgraphs, in SDM 2018 : Proceedings of the SIAM International Conference on Data Mining, Society for Industrial and Applied Mathematics, Philadelphia, Pa., pp. 306-314, doi: 10.1137/1.9781611975321.

Attached Files
Name Description MIMEType Size Downloads

Title Learning graph representation via frequent subgraphs
Author(s) Nguyen, Dang Pham Hai
Luo, WeiORCID iD for Luo, Wei orcid.org/0000-0002-4711-7543
Nguyen, Tu Dinh
Venkatesh, SvethaORCID iD for Venkatesh, Svetha orcid.org/0000-0001-8675-6631
Phung, Quoc-DinhORCID iD for Phung, Quoc-Dinh orcid.org/0000-0002-9977-8247
Conference name Data Mining. SIAM International Conference (2018 : San Diego, Calif.)
Conference location San Diego, Calif.
Conference dates 2018/05/03 - 2018/05/05
Title of proceedings SDM 2018 : Proceedings of the SIAM International Conference on Data Mining
Editor(s) Ester, M.
Pedreschi, D.
Publication date 2018
Start page 306
End page 314
Total pages 9
Publisher Society for Industrial and Applied Mathematics
Place of publication Philadelphia, Pa.
Summary © 2018 by SIAM. 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.
ISBN 9781611975321
Language eng
DOI 10.1137/1.9781611975321
HERDC Research category E1 Full written paper - refereed
Copyright notice ©2018, SIAM
Persistent URL http://hdl.handle.net/10536/DRO/DU:30109588

Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in TR Web of Science
Scopus Citation Count Cited 4 times in Scopus
Google Scholar Search Google Scholar
Access Statistics: 75 Abstract Views, 3 File Downloads  -  Detailed Statistics
Created: Thu, 28 Mar 2019, 12:53:01 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.