INCL: A Graph-based Recommendation Model Using Contrastive Learning for Inductive Scenario

• Item type: Journal(1)
• 公開日: 2024-11-15
• タイトル: INCL: A Graph-based Recommendation Model Using Contrastive Learning for Inductive Scenario
• タイトル / 言語: en
• タイトル: INCL: A Graph-based Recommendation Model Using Contrastive Learning for Inductive Scenario
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: [一般論文（推薦論文）] recommender system, collaborative filtering, inductive embedding, contrastive learning
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_6501
• 資源タイプ: journal article
• 著者所属: Osaka University
• 著者所属: KDDI Research, Inc.
• 著者所属: Osaka University
• 著者所属(英): en
• 著者所属(英): Osaka University
• 著者所属(英): en
• 著者所属(英): KDDI Research, Inc.
• 著者所属(英): en
• 著者所属(英): Osaka University
• 著者名: Yuma, Dose; Shuichiro, Haruta; Takahiro, Hara
• 著者名(英): Yuma, Dose; Shuichiro, Haruta; Takahiro, Hara
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: Graph-based recommendation models, which utilize a user-item interaction graph whose edges represent users' preferences, are well known because of their effectiveness. However, many existing models are intrinsically transductive, meaning they can make recommendations only for users and items that exist in training data. To solve this challenge, some researchers focus on recommendations in an inductive scenario where new users/items emerge in the inference phase. In this paper, we propose a contrastive learning framework for the inductive scenario, INductive Contrastive Learning (INCL). The situation where new users/items emerge can be interpreted as changes in the interaction graph. Therefore, it is crucial to capture the change in the interaction graph for inductive recommendations. Based on the perspective, INCL creates an augmented graph by adding or removing edges of the original interaction graph and simulates changes in the interaction graph. By performing contrastive learning, INCL fosters each representation generated from the original interaction graph and the augmented graph to be similar. As a result, INCL is trained to generate robust representations that can adapt to changes in the interaction graph. Experimental results on real-world datasets demonstrate that INCL outperforms existing models in the inductive scenario, achieving up to 2.13% improvement in Recall@20.; ------------------------------; This is a preprint of an article intended for publication Journal of; Information Processing(JIP). This preprint should not be cited. This; article should be cited as: Journal of Information Processing Vol.32(2024) (online); DOI http://dx.doi.org/10.2197/ipsjjip.32.929; ------------------------------
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: Graph-based recommendation models, which utilize a user-item interaction graph whose edges represent users' preferences, are well known because of their effectiveness. However, many existing models are intrinsically transductive, meaning they can make recommendations only for users and items that exist in training data. To solve this challenge, some researchers focus on recommendations in an inductive scenario where new users/items emerge in the inference phase. In this paper, we propose a contrastive learning framework for the inductive scenario, INductive Contrastive Learning (INCL). The situation where new users/items emerge can be interpreted as changes in the interaction graph. Therefore, it is crucial to capture the change in the interaction graph for inductive recommendations. Based on the perspective, INCL creates an augmented graph by adding or removing edges of the original interaction graph and simulates changes in the interaction graph. By performing contrastive learning, INCL fosters each representation generated from the original interaction graph and the augmented graph to be similar. As a result, INCL is trained to generate robust representations that can adapt to changes in the interaction graph. Experimental results on real-world datasets demonstrate that INCL outperforms existing models in the inductive scenario, achieving up to 2.13% improvement in Recall@20.; ------------------------------; This is a preprint of an article intended for publication Journal of; Information Processing(JIP). This preprint should not be cited. This; article should be cited as: Journal of Information Processing Vol.32(2024) (online); DOI http://dx.doi.org/10.2197/ipsjjip.32.929; ------------------------------
• 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: AN00116647
• 書誌情報: 情報処理学会論文誌; 巻 65, 号 11, 発行日 2024-11-15
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 1882-7764
• 公開者 / 言語: ja
• 公開者 / 出版者: 情報処理学会