Graph embedding using multi-layer adjacent point merging model

Jianming Huang, Hiroyuki Kasai

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

For graph classification tasks, many traditional kernel methods focus on measuring the similarity between graphs. These methods have achieved great success on resolving graph isomorphism problems. However, in some classification problems, the graph class depends on not only the topological similarity of the whole graph, but also constituent subgraph patterns. To this end, we propose a novel graph embedding method using a multi-layer adjacent point merging model. This embedding method allows us to extract different subgraph patterns from train-data. Then we present a flexible loss function for feature selection which enhances the robustness of our method for different classification problems. Finally, numerical evaluations demonstrate that our proposed method outperforms many state-of-the-art methods.

Original languageEnglish
Title of host publication2021 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2021 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages3585-3589
Number of pages5
ISBN (Electronic)9781728176055
DOIs
Publication statusPublished - 2021
Event2021 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2021 - Virtual, Toronto, Canada
Duration: 2021 Jun 62021 Jun 11

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
ISSN (Print)1520-6149

Conference

Conference2021 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2021
Country/TerritoryCanada
CityVirtual, Toronto
Period21/6/621/6/11

Keywords

  • Graph classification
  • Graph embedding
  • Graph kernel

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Graph embedding using multi-layer adjacent point merging model'. Together they form a unique fingerprint.

Cite this