A Wasserstein Graph Kernel based on Substructure Isomorphism Problem of Shortest Paths

• Item type: SIG Technical Reports(1)
• 公開日: 2020-11-19
• タイトル: A Wasserstein Graph Kernel based on Substructure Isomorphism Problem of Shortest Paths
• タイトル / 言語: en
• タイトル: A Wasserstein Graph Kernel based on Substructure Isomorphism Problem of Shortest Paths
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: 学生セッション
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_18gh
• 資源タイプ: technical report
• 著者所属: WASEDA University, Graduate School of Fundamental Science and Engineering
• 著者所属: WASEDA University, School of Fundamental Science and Engineering, Dept. of Communications and Computer Engineering
• 著者所属: WASEDA University, School of Fundamental Science and Engineering, Dept. of Communications and Computer Engineering
• 著者所属(英): en
• 著者所属(英): WASEDA University, Graduate School of Fundamental Science and Engineering
• 著者所属(英): en
• 著者所属(英): WASEDA University, School of Fundamental Science and Engineering, Dept. of Communications and Computer Engineering
• 著者所属(英): en
• 著者所属(英): WASEDA University, School of Fundamental Science and Engineering, Dept. of Communications and Computer Engineering
• 著者名: Jianming, Huang; Zhongxi, Fang; Hiroyuki, Kasai
• 著者名(英): Jianming, Huang; Zhongxi, Fang; Hiroyuki, Kasai
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: For graph classification tasks, many methods use a common strategy to aggregate information of vertex neighbors. Although this strategy provides an efficient means of extracting graph topological features, it brings excessive amounts of information that might greatly reduce its accuracy when dealing with large-scale neighborhoods. Learning graphs using paths or walks will not suffer from this difficulty, but many have low utilization of each path or walk, which might engender information loss and high computational costs. To solve this, we propose a graph kernel using a longest common subsequence (LCS kernel) to compute more comprehensive similarity between paths and walks, which resolves substructure isomorphism difficulties. We also combine it with optimal transport theory to extract more in-depth features of graphs.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: For graph classification tasks, many methods use a common strategy to aggregate information of vertex neighbors. Although this strategy provides an efficient means of extracting graph topological features, it brings excessive amounts of information that might greatly reduce its accuracy when dealing with large-scale neighborhoods. Learning graphs using paths or walks will not suffer from this difficulty, but many have low utilization of each path or walk, which might engender information loss and high computational costs. To solve this, we propose a graph kernel using a longest common subsequence (LCS kernel) to compute more comprehensive similarity between paths and walks, which resolves substructure isomorphism difficulties. We also combine it with optimal transport theory to extract more in-depth features of graphs.
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AN10438399
• 書誌情報: 研究報告オーディオビジュアル複合情報処理（AVM）; 巻 2020-AVM-111, 号 5, p. 1-4, 発行日 2020-11-19
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 2188-8582
• Notice: SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc.
• 出版者 / 言語: ja
• 出版者: 情報処理学会