Graph embedding using multi-layer adjacent point merging model

Jianming Huang, Hiroyuki Kasai*

*この研究の対応する著者

研究成果: Conference contribution

1 被引用数 (Scopus)

抄録

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.

本文言語English
ホスト出版物のタイトル2021 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2021 - Proceedings
出版社Institute of Electrical and Electronics Engineers Inc.
ページ3585-3589
ページ数5
ISBN(電子版)9781728176055
DOI
出版ステータスPublished - 2021
イベント2021 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2021 - Virtual, Toronto, Canada
継続期間: 2021 6 62021 6 11

出版物シリーズ

名前ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
ISSN(印刷版)1520-6149

Conference

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

ASJC Scopus subject areas

  • ソフトウェア
  • 信号処理
  • 電子工学および電気工学

フィンガープリント

「Graph embedding using multi-layer adjacent point merging model」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル