Dynamic Hyperbolic Embeddings with Graph-Centralized Regularization for Recommender Systems

• Item type: Trans(1)
• 公開日: 2021-10-14
• タイトル: Dynamic Hyperbolic Embeddings with Graph-Centralized Regularization for Recommender Systems
• タイトル / 言語: en
• タイトル: Dynamic Hyperbolic Embeddings with Graph-Centralized Regularization for Recommender Systems
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: [研究論文] recommender systems, hyperbolic embeddings, regularization, news service
• 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: Gunosy Inc.／Presently with University of Tsukuba
• 著者所属: University of Tsukuba
• 著者所属: Gunosy Inc.
• 著者所属(英): en
• 著者所属(英): Gunosy Inc. / Presently with University of Tsukuba
• 著者所属(英): en
• 著者所属(英): University of Tsukuba
• 著者所属(英): en
• 著者所属(英): Gunosy Inc.
• 著者名: Kojiro, Iizuka; Makoto, P. Kato; Yoshifumi, Seki
• 著者名(英): Kojiro, Iizuka; Makoto, P. Kato; Yoshifumi, Seki
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: In this work, we propose two techniques for accurate and efficient hyperbolic embeddings for real-world recommender systems. The first technique is regularization. We found that the graphs of various recommendation datasets exhibit hierarchical or tree-like structures suitable for hyperbolic embeddings, while these structures are not well modeled by the original hyperbolic embeddings. Hence, we introduce a regularization term in the objective function of the hyperbolic embeddings for forcibly reflecting hierarchical or tree-like structures. The second technique is an efficient embedding method, which only updates the embedding of items that are recently added in a recommender system. In an offline evaluation with various recommendation datasets, we found that the regularization enforcing hierarchical or tree-like structures improved HR@10 up to +9% compared to hyperbolic embeddings without the regularization. Moreover, the evaluation result showed that our model update technique could achieve not only greater efficiency but also more robustness. Finally, we applied our proposed techniques to a million-scale news recommendation service and conducted an A/B test, which demonstrated that even 10-dimension hyperbolic embeddings successfully increased the number of clicks by +3.7% and dwell time by +10%.; ------------------------------; 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.29(2021) (online); ------------------------------
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: In this work, we propose two techniques for accurate and efficient hyperbolic embeddings for real-world recommender systems. The first technique is regularization. We found that the graphs of various recommendation datasets exhibit hierarchical or tree-like structures suitable for hyperbolic embeddings, while these structures are not well modeled by the original hyperbolic embeddings. Hence, we introduce a regularization term in the objective function of the hyperbolic embeddings for forcibly reflecting hierarchical or tree-like structures. The second technique is an efficient embedding method, which only updates the embedding of items that are recently added in a recommender system. In an offline evaluation with various recommendation datasets, we found that the regularization enforcing hierarchical or tree-like structures improved HR@10 up to +9% compared to hyperbolic embeddings without the regularization. Moreover, the evaluation result showed that our model update technique could achieve not only greater efficiency but also more robustness. Finally, we applied our proposed techniques to a million-scale news recommendation service and conducted an A/B test, which demonstrated that even 10-dimension hyperbolic embeddings successfully increased the number of clicks by +3.7% and dwell time by +10%.; ------------------------------; 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.29(2021) (online); ------------------------------
• 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: AA11464847
• 書誌情報: 情報処理学会論文誌データベース（TOD）; 巻 14, 号 4, 発行日 2021-10-14
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 1882-7799
• 出版者 / 言語: ja
• 出版者: 情報処理学会