學術產出-Theses
Article View/Open
Publication Export
-
題名 基於翻譯序列推薦模型於跨領域推薦系統之強化方法
Employing Translation-based Recommendation for Improving Cross-domain Recommendation Performance作者 王均捷
Wang, Chun-Chieh貢獻者 蔡銘峰
Tsai, Ming-Feng
王均捷
Wang, Chun-Chieh關鍵詞 推薦系統
翻譯序列推薦
跨領域翻譯序列推薦
跨領域推薦
圖形學習
貝氏個人化推薦
recommendation system
TransRec
TransRecCross
cross-domain recommendation
graph learning
BPR日期 2021 上傳時間 1-Oct-2021 10:06:01 (UTC+8) 摘要 若我們有足夠多的歷史資料，就可以用很多不同的方法去建立一個聰明的推薦系統。但在某些情況下，比如一個新的社交媒體平台或電商平台上線時，我們沒有足夠的使用者物品互動資料來建構出好的推薦系統。其中一個強化跨領域推薦（cross-domain recommendation）的解決方案，是藉由將「來源領域（資訊含量較多之領域）」的資料加入「目標領域（資訊量相對較少的領域）」來提升資訊量，然後對「目標領域」進行推薦。本論文採用圖形學習表示演算法，結合改良並善用翻譯序列推薦模型（Translation-based Recommendation，TransRec）的推薦優勢，特化模型訓練時採樣方法、改變翻譯序列合併方法，並引入貝氏個人化推薦（Bayesian Personalized Ranking，BPR）中負採樣（negative sampling）的概念，訓練得到推薦系統任務導向之表示向量，藉此改善推薦結果。本研究旨在通過改良後的翻譯序列推薦模型「TransRecCross」來強化跨領域推薦效果。驗證本論文的新方法時，使用了 Amazon Review 系列資料集中的其中四個，並在論文最後比較了加入不同比例的來源領域資料後的推薦結果，以驗證本論文提出之方法的可靠程度。
There are plenty of ways to apply an intelligent domain-specific recommendation system if we have an enormous amount of data. Unfortunately, in some scenarioslike running a new social media platform or online store, we do not have enough user-item interactions data to build a sound recommendation system. One of the solutions is to apply cross-domain recommendation techniques: we can increase the amount of information by gathering the user-item interaction information from the "source domain" into the "target domain," and then implement therecommendation system based on the "target domain."This thesis adopts graph learning representation algorithm with extending the advantages of TransRec (Translation-based Recommendation): specializes the sampling method, changes the translating method, and then applies the negative sampling concept of BPR (Bayesian Personalized Ranking), then train and get the recommendation-oriented representation vectors to improve the recommendation system performance. This study aims to improve the cross-domain recommendation performance via a reformed translation-based recommendation model named "TransRecCross." In our experiments, comprehensive comparisons conducted on four datasets from Amazon Review have verified the effectiveness of the proposed TransRecCross.參考文獻 [1] P. H. Aditya, I. Budi, and Q. Munajat. A comparative analysis of memory-based and model-based collaborative filtering on the implementation of recommender system for e-commerce in indonesia: A case study pt x. In 2016 International Conference on Advanced Computer Science and Information Systems (ICACSIS), pages 303–308, 2016.[2] A. Bordes, N. Usunier, A. Garcia-Duran, J. Weston, and O. Yakhnenko. Translating embeddings for modeling multi-relational data. In C. J. C. Burges, L. Bottou, M. Welling, Z. Ghahramani, and K. Q. Weinberger, editors, Advances in Neural Information Processing Systems, volume 26. Curran Associates, Inc., 2013.[3] C.-M. Chen, M.-F. Tsai, Y.-C. Lin, and Y.-H. Yang. Query-based music recommendations via preference embedding. In Proceedings of the 10th ACM Conference on Recommender Systems, RecSys ’16, page 79–82, New York, NY, USA, 2016. Association for Computing Machinery.[4] C.-M. Chen, C.-J. Wang, M.-F. Tsai, and Y.-H. Yang. Collaborative similarity embedding for recommender systems. In The World Wide Web Conference, WWW ’19, page 2637–2643, New York, NY, USA, 2019. Association for Computing Machinery.[5] Francesco Ricci, Lior Rokach, Bracha Shapira, and Paul Kantor. Recommender systems handbook. 2011.[6] A. Grover and J. Leskovec. node2vec: Scalable feature learning for networks, 2016.[7] G. Guo, H. Wang, D. Bell, Y. Bi, and K. Greer. Knn model-based approach in classification. In R. Meersman, Z. Tari, and D. C. Schmidt, editors, On The Move to Meaningful Internet Systems 2003: CoopIS, DOA, and ODBASE, pages 986–996, Berlin, Heidelberg, 2003. Springer Berlin Heidelberg.[8] R. He, W.-C. Kang, and J. McAuley. Translation-based recommendation. Proceedings of the Eleventh ACM Conference on Recommender Systems, Aug 2017[9] A. Krohn-Grimberghe, L. Drumond, C. Freudenthaler, and L. Schmidt-Thieme. Multi-relational matrix factorization using bayesian personalized ranking for social network data. In Proceedings of the Fifth ACM International Conference on Web Search and Data Mining, WSDM ’12, page 173–182, New York, NY, USA, 2012. Association for Computing Machinery.[10] O. Kuchaiev and B. Ginsburg. Training deep autoencoders for collaborative filtering, 2017.[11] Y. Lin, Z. Liu, M. Sun, Y. Liu, and X. Zhu. Learning entity and relation embeddings for knowledge graph completion. In Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence, AAAI’15, page 2181–2187. AAAI Press, 2015.[12] W. Lu, F. lai Chung, K. Lai, and L. Zhang. Recommender system based on scarce information mining. Neural Networks, 93:256–266, 2017.[13] T. Man, H. Shen, X. Jin, and X. Cheng. Cross-domain recommendation: An embedding and mapping approach. In Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, IJCAI-17, pages 2464–2470, 2017.[14] X. Ning and G. Karypis. Slim: Sparse linear methods for top-n recommender systems. In 2011 IEEE 11th International Conference on Data Mining, pages 497–506, 2011.[15] R. Pan, Y. Zhou, B. Cao, N. N. Liu, R. Lukose, M. Scholz, and Q. Yang. Oneclass collaborative filtering. In Proceedings of the 2008 Eighth IEEE International Conference on Data Mining, ICDM ’08, page 502–511, USA, 2008. IEEE Computer Society.[16] B. Perozzi, R. Al-Rfou, and S. Skiena. Deepwalk: Online learning of social representations. In Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’14, page 701–710, New York, NY, USA, 2014. Association for Computing Machinery.[17] J. Ramos. Using tf-idf to determine word relevance in document queries, 1999.[18] S. Rendle and C. Freudenthaler. Improving pairwise learning for item recommendation from implicit feedback. In Proceedings of the 7th ACM International Conference on Web Search and Data Mining, WSDM ’14, page 273–282, New York, NY, USA, 2014. Association for Computing Machinery.[19] S. Rendle, C. Freudenthaler, Z. Gantner, and L. Schmidt-Thieme. Bpr: Bayesian personalized ranking from implicit feedback. In Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence, UAI ’09, page 452–461, Arlington, Virginia, USA, 2009. AUAI Press.[20] S. Rendle and L. Schmidt-Thieme. Pairwise interaction tensor factorization for personalized tag recommendation. In Proceedings of the Third ACM International Conference on Web Search and Data Mining, WSDM ’10, page 81–90, New York, NY, USA, 2010. Association for Computing Machinery.[21] J. Tang, M. Qu, M. Wang, M. Zhang, J. Yan, and Q. Mei. Line: Large-scale information network embedding. In Proceedings of the 24th International Conference on World Wide Web, WWW ’15, page 1067–1077, Republic and Canton of Geneva, CHE, 2015. International World Wide Web Conferences Steering Committee.[22] K. Taunk, S. De, S. Verma, and A. Swetapadma. A brief review of nearest neighbor algorithm for learning and classification. In 2019 International Conference on Intelligent Computing and Control Systems (ICCS), pages 1255–1260, 2019.[23] D. H. Tran, Z. Hussain, W. E. Zhang, N. L. D. Khoa, N. H. Tran, and Q. Z. Sheng. Deep autoencoder for recommender systems: Parameter influence analysis, 2018.[24] Z. Wang, J. Zhang, J. Feng, and Z. Chen. Knowledge graph embedding by translating on hyperplanes. In Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence, AAAI’14, page 1112–1119. AAAI Press, 2014.[25] J.-H. Yang, C.-M. Chen, C.-J. Wang, and M.-F. Tsai. Hop-rec: High-order proximity for implicit recommendation. In Proceedings of the 12th ACM Conference on Recommender Systems, RecSys ’18, page 140–144, New York, NY, USA, 2018. Association for Computing Machinery.[26] S. Zhang, L. Yao, A. Sun, and Y. Tay. Deep learning based recommender system. ACM Computing Surveys, 52(1):1–38, Feb 2019. [27] X. Zhang. Toprec: Domain-specific recommendation through community topic mining in social network. 05 2013.[28] Y. Zhang and X. Chen. Explainable recommendation: A survey and new perspectives. Foundations and Trends® in Information Retrieval, 14(1):1–101, 2020.[29] C. Zhou, Y. Liu, X. Liu, Z. Liu, and J. Gao. Scalable graph embedding for asymmetric proximity. In Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, AAAI’17, page 2942–2948. AAAI Press, 2017.[30] F. Zhu, Y. Wang, C. Chen, J. Zhou, L. Li, and G. Liu. Cross-domain recommendation: Challenges, progress, and prospects, 2021. 描述 碩士
國立政治大學
資訊科學系
108753113資料來源 http://thesis.lib.nccu.edu.tw/record/#G0108753113 資料類型 thesis dc.contributor.advisor 蔡銘峰 zh_TW dc.contributor.advisor Tsai, Ming-Feng en_US dc.contributor.author (Authors) 王均捷 zh_TW dc.contributor.author (Authors) Wang, Chun-Chieh en_US dc.creator (作者) 王均捷 zh_TW dc.creator (作者) Wang, Chun-Chieh en_US dc.date (日期) 2021 en_US dc.date.accessioned 1-Oct-2021 10:06:01 (UTC+8) - dc.date.available 1-Oct-2021 10:06:01 (UTC+8) - dc.date.issued (上傳時間) 1-Oct-2021 10:06:01 (UTC+8) - dc.identifier (Other Identifiers) G0108753113 en_US dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/137295 - dc.description (描述) 碩士 zh_TW dc.description (描述) 國立政治大學 zh_TW dc.description (描述) 資訊科學系 zh_TW dc.description (描述) 108753113 zh_TW dc.description.abstract (摘要) 若我們有足夠多的歷史資料，就可以用很多不同的方法去建立一個聰明的推薦系統。但在某些情況下，比如一個新的社交媒體平台或電商平台上線時，我們沒有足夠的使用者物品互動資料來建構出好的推薦系統。其中一個強化跨領域推薦（cross-domain recommendation）的解決方案，是藉由將「來源領域（資訊含量較多之領域）」的資料加入「目標領域（資訊量相對較少的領域）」來提升資訊量，然後對「目標領域」進行推薦。本論文採用圖形學習表示演算法，結合改良並善用翻譯序列推薦模型（Translation-based Recommendation，TransRec）的推薦優勢，特化模型訓練時採樣方法、改變翻譯序列合併方法，並引入貝氏個人化推薦（Bayesian Personalized Ranking，BPR）中負採樣（negative sampling）的概念，訓練得到推薦系統任務導向之表示向量，藉此改善推薦結果。本研究旨在通過改良後的翻譯序列推薦模型「TransRecCross」來強化跨領域推薦效果。驗證本論文的新方法時，使用了 Amazon Review 系列資料集中的其中四個，並在論文最後比較了加入不同比例的來源領域資料後的推薦結果，以驗證本論文提出之方法的可靠程度。 zh_TW dc.description.abstract (摘要) There are plenty of ways to apply an intelligent domain-specific recommendation system if we have an enormous amount of data. Unfortunately, in some scenarioslike running a new social media platform or online store, we do not have enough user-item interactions data to build a sound recommendation system. One of the solutions is to apply cross-domain recommendation techniques: we can increase the amount of information by gathering the user-item interaction information from the "source domain" into the "target domain," and then implement therecommendation system based on the "target domain."This thesis adopts graph learning representation algorithm with extending the advantages of TransRec (Translation-based Recommendation): specializes the sampling method, changes the translating method, and then applies the negative sampling concept of BPR (Bayesian Personalized Ranking), then train and get the recommendation-oriented representation vectors to improve the recommendation system performance. This study aims to improve the cross-domain recommendation performance via a reformed translation-based recommendation model named "TransRecCross." In our experiments, comprehensive comparisons conducted on four datasets from Amazon Review have verified the effectiveness of the proposed TransRecCross. en_US dc.description.tableofcontents 第一章 緒論 11.1 前言 11.2 研究目的 2第二章 相關文獻探討 42.1 圖形學習表示法 42.2 個人化推薦系統 52.3 跨領域推薦 7第三章 研究方法 93.1 問題定義 93.1.1 先備知識 93.1.2 研究動機 123.2 TransRecCross模型 133.2.1 符號定義 133.2.2 模型介紹 143.2.3 採樣細節分析 17第四章 實驗結果與討論 194.1 資料集 194.2 比較基準模型 204.3 實驗設定與驗證標準 224.3.1 實驗設定 224.3.2 驗證標準 224.4 實驗結果 244.4.1 跨領域推薦領域結果 244.4.2 驗證跨領域強化能力 27第五章 結論 31參考文獻 32 zh_TW dc.format.extent 1940359 bytes - dc.format.mimetype application/pdf - dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0108753113 en_US dc.subject (關鍵詞) 推薦系統 zh_TW dc.subject (關鍵詞) 翻譯序列推薦 zh_TW dc.subject (關鍵詞) 跨領域翻譯序列推薦 zh_TW dc.subject (關鍵詞) 跨領域推薦 zh_TW dc.subject (關鍵詞) 圖形學習 zh_TW dc.subject (關鍵詞) 貝氏個人化推薦 zh_TW dc.subject (關鍵詞) recommendation system en_US dc.subject (關鍵詞) TransRec en_US dc.subject (關鍵詞) TransRecCross en_US dc.subject (關鍵詞) cross-domain recommendation en_US dc.subject (關鍵詞) graph learning en_US dc.subject (關鍵詞) BPR en_US dc.title (題名) 基於翻譯序列推薦模型於跨領域推薦系統之強化方法 zh_TW dc.title (題名) Employing Translation-based Recommendation for Improving Cross-domain Recommendation Performance en_US dc.type (資料類型) thesis en_US dc.relation.reference (參考文獻) [1] P. H. Aditya, I. Budi, and Q. Munajat. A comparative analysis of memory-based and model-based collaborative filtering on the implementation of recommender system for e-commerce in indonesia: A case study pt x. In 2016 International Conference on Advanced Computer Science and Information Systems (ICACSIS), pages 303–308, 2016.[2] A. Bordes, N. Usunier, A. Garcia-Duran, J. Weston, and O. Yakhnenko. Translating embeddings for modeling multi-relational data. In C. J. C. Burges, L. Bottou, M. Welling, Z. Ghahramani, and K. Q. Weinberger, editors, Advances in Neural Information Processing Systems, volume 26. Curran Associates, Inc., 2013.[3] C.-M. Chen, M.-F. Tsai, Y.-C. Lin, and Y.-H. Yang. Query-based music recommendations via preference embedding. In Proceedings of the 10th ACM Conference on Recommender Systems, RecSys ’16, page 79–82, New York, NY, USA, 2016. Association for Computing Machinery.[4] C.-M. Chen, C.-J. Wang, M.-F. Tsai, and Y.-H. Yang. Collaborative similarity embedding for recommender systems. In The World Wide Web Conference, WWW ’19, page 2637–2643, New York, NY, USA, 2019. Association for Computing Machinery.[5] Francesco Ricci, Lior Rokach, Bracha Shapira, and Paul Kantor. Recommender systems handbook. 2011.[6] A. Grover and J. Leskovec. node2vec: Scalable feature learning for networks, 2016.[7] G. Guo, H. Wang, D. Bell, Y. Bi, and K. Greer. Knn model-based approach in classification. In R. Meersman, Z. Tari, and D. C. Schmidt, editors, On The Move to Meaningful Internet Systems 2003: CoopIS, DOA, and ODBASE, pages 986–996, Berlin, Heidelberg, 2003. Springer Berlin Heidelberg.[8] R. He, W.-C. Kang, and J. McAuley. Translation-based recommendation. Proceedings of the Eleventh ACM Conference on Recommender Systems, Aug 2017[9] A. Krohn-Grimberghe, L. Drumond, C. Freudenthaler, and L. Schmidt-Thieme. Multi-relational matrix factorization using bayesian personalized ranking for social network data. In Proceedings of the Fifth ACM International Conference on Web Search and Data Mining, WSDM ’12, page 173–182, New York, NY, USA, 2012. Association for Computing Machinery.[10] O. Kuchaiev and B. Ginsburg. Training deep autoencoders for collaborative filtering, 2017.[11] Y. Lin, Z. Liu, M. Sun, Y. Liu, and X. Zhu. Learning entity and relation embeddings for knowledge graph completion. In Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence, AAAI’15, page 2181–2187. AAAI Press, 2015.[12] W. Lu, F. lai Chung, K. Lai, and L. Zhang. Recommender system based on scarce information mining. Neural Networks, 93:256–266, 2017.[13] T. Man, H. Shen, X. Jin, and X. Cheng. Cross-domain recommendation: An embedding and mapping approach. In Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, IJCAI-17, pages 2464–2470, 2017.[14] X. Ning and G. Karypis. Slim: Sparse linear methods for top-n recommender systems. In 2011 IEEE 11th International Conference on Data Mining, pages 497–506, 2011.[15] R. Pan, Y. Zhou, B. Cao, N. N. Liu, R. Lukose, M. Scholz, and Q. Yang. Oneclass collaborative filtering. In Proceedings of the 2008 Eighth IEEE International Conference on Data Mining, ICDM ’08, page 502–511, USA, 2008. IEEE Computer Society.[16] B. Perozzi, R. Al-Rfou, and S. Skiena. Deepwalk: Online learning of social representations. In Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’14, page 701–710, New York, NY, USA, 2014. Association for Computing Machinery.[17] J. Ramos. Using tf-idf to determine word relevance in document queries, 1999.[18] S. Rendle and C. Freudenthaler. Improving pairwise learning for item recommendation from implicit feedback. In Proceedings of the 7th ACM International Conference on Web Search and Data Mining, WSDM ’14, page 273–282, New York, NY, USA, 2014. Association for Computing Machinery.[19] S. Rendle, C. Freudenthaler, Z. Gantner, and L. Schmidt-Thieme. Bpr: Bayesian personalized ranking from implicit feedback. In Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence, UAI ’09, page 452–461, Arlington, Virginia, USA, 2009. AUAI Press.[20] S. Rendle and L. Schmidt-Thieme. Pairwise interaction tensor factorization for personalized tag recommendation. In Proceedings of the Third ACM International Conference on Web Search and Data Mining, WSDM ’10, page 81–90, New York, NY, USA, 2010. Association for Computing Machinery.[21] J. Tang, M. Qu, M. Wang, M. Zhang, J. Yan, and Q. Mei. Line: Large-scale information network embedding. In Proceedings of the 24th International Conference on World Wide Web, WWW ’15, page 1067–1077, Republic and Canton of Geneva, CHE, 2015. International World Wide Web Conferences Steering Committee.[22] K. Taunk, S. De, S. Verma, and A. Swetapadma. A brief review of nearest neighbor algorithm for learning and classification. In 2019 International Conference on Intelligent Computing and Control Systems (ICCS), pages 1255–1260, 2019.[23] D. H. Tran, Z. Hussain, W. E. Zhang, N. L. D. Khoa, N. H. Tran, and Q. Z. Sheng. Deep autoencoder for recommender systems: Parameter influence analysis, 2018.[24] Z. Wang, J. Zhang, J. Feng, and Z. Chen. Knowledge graph embedding by translating on hyperplanes. In Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence, AAAI’14, page 1112–1119. AAAI Press, 2014.[25] J.-H. Yang, C.-M. Chen, C.-J. Wang, and M.-F. Tsai. Hop-rec: High-order proximity for implicit recommendation. In Proceedings of the 12th ACM Conference on Recommender Systems, RecSys ’18, page 140–144, New York, NY, USA, 2018. Association for Computing Machinery.[26] S. Zhang, L. Yao, A. Sun, and Y. Tay. Deep learning based recommender system. ACM Computing Surveys, 52(1):1–38, Feb 2019. [27] X. Zhang. Toprec: Domain-specific recommendation through community topic mining in social network. 05 2013.[28] Y. Zhang and X. Chen. Explainable recommendation: A survey and new perspectives. Foundations and Trends® in Information Retrieval, 14(1):1–101, 2020.[29] C. Zhou, Y. Liu, X. Liu, Z. Liu, and J. Gao. Scalable graph embedding for asymmetric proximity. In Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, AAAI’17, page 2942–2948. AAAI Press, 2017.[30] F. Zhu, Y. Wang, C. Chen, J. Zhou, L. Li, and G. Liu. Cross-domain recommendation: Challenges, progress, and prospects, 2021. zh_TW dc.identifier.doi (DOI) 10.6814/NCCU202101565 en_US
