Presentation 2020-03-11
Subspace Representation for Graphs
Junki Ishikawa, Hiroaki Shiokawa, Kazuhiro Fukui,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this research, we discuss a representation learning for graph analysis, where a graph is represented by a low dimensional subspace in a high vector space. This subspace representation allows us to calculate easily the structural similarity between graphs with showing the importance degree of each graph node in the similar- ity calculation. We demonstrate the effectiveness of our method on three benchmark databases related to graph classification, outperforming several conventional representation learning methods.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) graph / graph embedding / representation learning on graphs
Paper # IBISML2019-40
Date of Issue 2020-03-03 (IBISML)

Conference Information
Committee IBISML
Conference Date 2020/3/10(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Kyoto University
Topics (in Japanese) (See Japanese page)
Topics (in English) Machine learning, etc.
Chair Hisashi Kashima(Kyoto Univ.)
Vice Chair Masashi Sugiyama(Univ. of Tokyo) / Koji Tsuda(Univ. of Tokyo)
Secretary Masashi Sugiyama(Nagoya Inst. of Tech.) / Koji Tsuda(AIST)
Assistant Tomoharu Iwata(NTT) / Shigeyuki Oba(Kyoto Univ.)

Paper Information
Registration To Technical Committee on Infomation-Based Induction Sciences and Machine Learning
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Subspace Representation for Graphs
Sub Title (in English)
Keyword(1) graph
Keyword(2) graph embedding
Keyword(3) representation learning on graphs
1st Author's Name Junki Ishikawa
1st Author's Affiliation University of Tsukuba(Tsukuba Univ.)
2nd Author's Name Hiroaki Shiokawa
2nd Author's Affiliation University of Tsukuba(Tsukuba Univ.)
3rd Author's Name Kazuhiro Fukui
3rd Author's Affiliation University of Tsukuba(Tsukuba Univ.)
Date 2020-03-11
Paper # IBISML2019-40
Volume (vol) vol.119
Number (no) IBISML-476
Page pp.pp.51-57(IBISML),
#Pages 7
Date of Issue 2020-03-03 (IBISML)