A Probability Distribution Learning Method for Extracting Key Vertex Pairs in Graph Classification Tasks

• Item type: SIG Technical Reports(1)
• 公開日: 2021-11-18
• タイトル: A Probability Distribution Learning Method for Extracting Key Vertex Pairs in Graph Classification Tasks
• タイトル / 言語: en
• タイトル: A Probability Distribution Learning Method for Extracting Key Vertex Pairs in Graph Classification Tasks
• 言語: eng
• 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: Graph classification is a hot topic of machine learning for graph-structured data, and it is also a very potential and valuable research because it has a wide range of applications such as bioinformatics, computer vision, social networks, and so on. However, the difficulty of graph classification is challenging and special, which is different from the ones of normal classification problems. One of the most difficult points of graph classification is that, the number of vertex neighbors in a graph tends to be variable, which makes the number of weights uncertain and ambiguous. In order to overcome these difficulties, we propose a novel method which weights the vertex neighbors based on a weighting function by learning the probability distributions of vertex pairs. The numerical evaluations show that our proposed method outperforms many state-of-the-art methods including some deep learning methods.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: Graph classification is a hot topic of machine learning for graph-structured data, and it is also a very potential and valuable research because it has a wide range of applications such as bioinformatics, computer vision, social networks, and so on. However, the difficulty of graph classification is challenging and special, which is different from the ones of normal classification problems. One of the most difficult points of graph classification is that, the number of vertex neighbors in a graph tends to be variable, which makes the number of weights uncertain and ambiguous. In order to overcome these difficulties, we propose a novel method which weights the vertex neighbors based on a weighting function by learning the probability distributions of vertex pairs. The numerical evaluations show that our proposed method outperforms many state-of-the-art methods including some deep learning methods.
• 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 2021-AVM-115, 号 12, p. 1-4, 発行日 2021-11-18
• 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