成功大學博碩士論文系統

簡易檢索 / 詳目顯示

回結果列表

研究生：	馬豪尚 Ma, Hao-Shang
論文名稱：	應用於推薦未來K個物品推薦系統的使用者偏好翻譯模型 User Preference Translation Model for Next-k Items Recommendation
指導教授：	黃仁暐 Huang, Jen-Wei
學位類別：	博士 Doctor
系所名稱：	電機資訊學院 - 電腦與通信工程研究所 Institute of Computer & Communication Engineering
論文出版年：	2022
畢業學年度：	110
語文別：	英文
論文頁數：	66
中文關鍵詞：	推薦系統、社群推薦、下k個物品物測
外文關鍵詞：	Recommendation Systems, Social Recommendation, Next-k Item Prediction
相關次數：	點閱：65 下載：0
分享至:	分享至facebook 分享至twitter

查詢本校圖書館目錄查詢臺灣博碩士論文知識加值系統勘誤回報

在過去的推薦系統中，Top-k推薦系統通常是針對使用者的潛在偏好做探索，推薦使用者可能最有興趣的k個物品；而Next item預測的推薦系統是根據使用者最近的互動物品來推薦下一個使用者可能會有興趣的物品。在實際的例子中，我們認為物品之間的存在彼此影響的關係並且有些重要的物品會誘使使用者對某些其他的物品產生極大的興趣，我們稱之為觸發關係，因使我們透過社群影響力傳遞技術來模擬物品之間的觸發關係。所以我們也因此想要推薦使用者未來會互動的一系列物品，在本論文中，我們就討論了我們對 next-k 推薦問題的定義。然後，為了解決過往Top-k推薦系統在學習使用者和物品的表示式之後，模型在之後的推薦時必須要花大量的計算時間來計算使用者和物品的相似程度，因而我們提出了使用者偏好翻譯模型來學習使用者的潛在偏好並直接預測未來的行為。此外，我們還研究了社群推薦系統。基於來自社群網站的資訊，可以開發推薦系統來預測使用者偏好並推薦使用者喜歡的物品或項目傳統的社群推薦系統通常會根據熱門程度、熟悉度和相似度等重要因素生成推薦列表。在此論文中，我們基於原本的使用者偏好翻譯模型，加入考量使用者之間的社群關係來達到社群推薦的 next-k 推薦。

In the past recommendation systems, the Top-k recommendation system usually explores the user's potential preferences and recommends k items that the user may be most interested in; while the recommendation system for Next item prediction is based on the user's most recent interactive items to recommend items that the next user might be interested in. In practical examples, we think that there is a relationship between items that affects each other and some important items will induce users to have a great interest in some other items. This phenomenon is defined as a trigger relationship. We propose to simulate trigger relationships between items through the social influence diffusion technology. In addition, we want to recommend a series of items that users will interact with in the future. Therefore, in this dissertation, we discuss the our proposal for the next-k recommendation problem. Then, in order to solve the problem that after learning the expressions of users and items in the past Top-k recommendation systems, the model must spend a lot of computing time to calculate the similarity between users and items in subsequent recommendations. Therefore, we propose a user Preference translation models to learn users' latent preferences and directly predict future behaviors.In addition, we also study social recommender systems. Based on information from social networking sites, recommender systems can be developed to predict user preferences and recommend items or items that users like. Traditional social recommendation systems usually generate recommendation lists based on important factors such as popularity, familiarity, and similarity. In this paper, based on the original user preference translation model, we consider the social relationship between users to achieve the next-k recommendation for social recommendation.

中文摘要 i
Abstract  ii
Acknowledgements iv
Contents  v
List of Tables  viii
List of Figures ix
Introduction 1
1 Motivations 1
2 Overview of the Dissertation 3
2.1 User Preference Translation Model for Recommendation System with Item Influence Diffusion Embedding 4
2.2 Unknown But Interesting Recommendation Using Social Penetration 5
2.3 User Preference Translation Model for Next-k Social Recommendation System 6
User Preference Translation Model for Recommendation System with Item
Influence Diffusion Embedding 8
1 Introduction 8
2 Related Works 11
2.1 Item embedding-based Recommendation 11
2.2 Collaborative Filtering with Deep Neural Network for Top-k Recommendation 12
3 Methodology 13
3.1 Next-k items Prediction Problem Formulation 13
3.2 The Model Architecture 14
3.3 Item Influence Diffusion Embedding 14
3.4 User Preference Translation Model 17
4 Experiments 19
4.1 Experiment Setting 22
4.2 Overall Performance Comparison (RQ1) 25
4.3 Ablation Study of UPTM (RQ2) 29
4.4 Hyper-parameters Analysis in UPTM (RQ3) 29
4.5 Costing Time Comparison (RQ4) 31
4.6 Case study (RQ5) 32
5 Conclusion of this work 33
User Preference Translation Model for Next-k Social Recommendation System 34
1 Introduction 34
2 Related Works 37
2.1 Item embedding-based Recommendation 37
2.2 Sequential-based Next Item Recommendation 38
2.3 Collaborative Filtering for Top-k Recommendation 38
2.4 Social Recommendation Systems 39
3 Methodology 41
3.1 Next-k Recommendation Problem Formulation 41
3.2 The Model Architecture 42
3.3 Item Influence Diffusion Embedding 42
3.4 User Social Embedding 45
3.5 User Preference Translation Model for Social Recommendation 46
4 Experiments 49
4.1 Experiment Setting 51
4.2 Overall Performance Comparison (RQ1) 54
4.3 Ablation Study of UPTMSR (RQ2) 56
4.4 Hyper-parameters Analysis and Disscusion of UPTMSR (RQ3) 57
5 Conclusions of this work 58
Conclusions 59
Future Works 60
References 61
                                    

[1] Carlos A. Gomez-Uribe and Neil Hunt. The netflix recommender system: Algorithms, business value,and innovation. ACM Transactions on Management Information Systems, 6(4), 2015.
[2] James Davidson, Benjamin Liebald, Junning Liu, Palash Nandy, Taylor Van Vleet, Ullas Gargi, Sujoy Gupta, Yu He, Mike Lambert, BlakeLivingston, and Dasarathi Sampath. The youtube video recommendation system. In Proceedings of the fourth ACM conference on Recommender systems, pages 293–296, 2010.
[3] Qijie Shen, Hong Wen, Wanjie Tao, Jing Zhang, Fuyu Lv, Zulong Chen, and Zhao Li. Deep interest highlight network for click-through rate prediction in triggerinduced recommendation. In Proceedings of the 31th International Conference on World Wide Web, 2022.
[4] Steffen Rendle, Christoph Freudenthaler, Zeno Gantner, and Lars Schmidt-Thieme. Bpr: Bayesian personalized ranking from implicit feedback. In Proceedings of the twenty-fifth conference on uncertainty in artificial intelligence, 2009.
[5] Xiangnan He, Lizi Liao, Hanwang Zhang, Liqiang Nie, Xia Hu, and Tat-Seng Chua. Neural collaborative filtering. In Proceedings of the International World Wide Web Conference, pages 173–182, 2017.
[6] Xiang Wang, Xiangnan He, Meng Wang, Fuli Feng, and Tat-Seng Chua. Neural graph collaborative filtering. In Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 165–174, 2019.
[7] Chuan-Ju Wang, Ting-Hsiang Wang, Hsiu-Wei Yang, Bo-Sin Chang, and Ming-Feng Tsai. Ice: Item concept embedding via textual information. In Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 85–94, 2016.
[8] D. Kempe, J. Kleinberg, and E. Tardos. Maximizing the spread of influence through a social network. In Proceedings of the 9th ACM SIGKDD international conference on Knowledge discovery and data mining, pages 137–146, 2003.
[9] Menghan Wang, Xiaolin Zheng, Yang Yang, and Kun Zhang. Collaborative filtering with social exposure: A modular approach to social recommendation. In Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, pages 2516–2523, 2018.
[10] Slobodan Vucetic and Zoran Obradovic. Collaborative filtering using a regressionbased approach. Knowledge and Information Systems, 7:1–22, 2005.
[11] ShoujinWang, Liang Hu, Longbing Cao, Xiaoshui Huang, Defu Lian, andWei Liu. Attention-based transactional context embedding for next-item recommendation. In Proceedings of Association for the Advancement of Artificial Intelligence, pages 2532–2539, 2018.
[12] Zhaoqiang Li, Jiajin Huang, and Ning Zhong. Exploiting user and item embedding in latent factor models for recommendations. In Proceedings of the International Conference on Web IntelligenceAugust, pages 1241–1245, 2017.
[13] Weizheng Chen, Xianling Mao, Xiangyu Li, Yan Zhang, and Xiaoming Li. Pne: Label embedding enhanced network embedding. In Proceedings of Pacic-Asia Conference on Knowledge Discovery and Data Mining, pages 547–560, 2017.
[14] Daheng Wang, Meng Jiang, Qingkai Zeng, Zachary Eberhart, and Nitesh V. Chawla. Multi-type itemset embedding for learning behavior success. In Proceedings of the 24th SIGKDD Conference on Knowledge Discovery and Data Mining, pages 2397–2406, 2018.
[15] Yehuda Koren, Robert M. Bell, and Chris Volinsky. Matrix factorizationtechniques for recommender systems. Computer, 42:30–37, 2009.
[16] Hongwei Wang, Jia Wang, Jialin Wang, Miao Zhao, Weinan Zhang, Fuzheng Zhang, Xing Xie, and Minyi Guo. Graphgan: Graph representation learning withgenerative adversarial nets. In Proceedings of the 32nd AAAI Conference on Artificial Intelligence, 2018.
[17] Jun Wang, Lantao Yu, Weinan Zhang, Yu Gong, Yinghui Xu, Benyou Wang, Peng Zhang, and Dell Zhang. A minimax game for unifying generative anddiscriminative information retrieval models. In Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 515–524, 2017.
[18] Dong-Kyu Chae, Jinsoo Kang, Jin-Soo Kang, Sang-Wook Kim, Jungtae Lee, and Jung-Tae Lee. Cfgan: A generic collaborative filtering framework based on generative adversarial networks. In Proceedings of the 27th ACM International Conference on Information and Knowledge Management, pages 137–146, 2018.
[19] Wei Chen, Chi Wang, and Yajun Wang. Scalable influence maximization for prevalent viral marketing in large-scale social networks. In Proceedings of the 16th ACM SIGKDD international conference on Knowledge discovery and data mining, pages 1029–1038, 2010.
[20] Ashish Vaswani, Noam Shazeer adn Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. Attention is all you need. In Proceedings of Advances in Neural Information Processing Systems, pages 5998–6008, 2017.
[21] Dan Hendrycks and Kevin Gimpel. Bridging nonlinearities and stochasticregularizers with gaussian error linear units. In CoRR abs/1606.08415, 2016.
[22] Angela Fan, Mike Lewis, and Yann Dauphin. Hierarchical neural story generation. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, pages 889–898, 2018.
[23] Ruining He and Julian McAuley. Ups and downs: Modeling the visual evolution of fashion trends with one-class collaborative filtering. In Proceedings of the 25th International Conference on World Wide Web, pages 507–517, 2016.
[24] Qiao Liu, Yifu Zeng, Refuoe Mokhosi, and Haibin Zhang. Stamp: Short-term attention/memory priority model for session-based recommendation. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pages 1831–1839, 2018.
[25] Massimo Quadrana, Alexandros Karatzoglou, Bal´azs Hidasi, and Paolo Cremonesi. Personalizing session-based recommendations with hierarchical recurrent neural networks. In Proceedings of the Eleventh ACM Conference on Recommender Systems, pages 130–137, 2017.
[26] Haochao Ying, Fuzhen Zhuang, Fuzheng Zhang, Yanchi Liu, Guandong Xu, Xing Xie, Hui Xiong, and Jian Wu. Sequential recommender system based on hierarchical attention networks. In the 27th International Joint Conference on Artificial Intelligence, pages 3926–3932, 2018.
[27] Jing Li, Pengjie Ren, Zhumin Chen, Zhaochun Ren, Tao Lian, and Jun Ma. Neural attentive session-based recommendation. In Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, pages 1419–1428, 2017.
[28] Feng Yu, Qiang Liu, Shu Wu, Liang Wang, and Tieniu Tan. A dynamic recurrent model for next basket recommendation. In Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval, pages 729–732, 2016.
[29] Tong Zhao, Julian McAuley, and Irwin King. Leveraging social connections to improve personalized ranking for collaborative filtering. In Proceedings of the 23rd ACM Conference on Information and Knowledge Management, pages 261–270, 2014.
[30] Shuyi Ji, Yifan Feng, Rongrong Ji, Xibin Zhao, Wanwan Tang, and Yue Gao. Dual channel hypergraph collaborative filtering. In Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pages 2020–2029, 2020.
[31] Junliang Yu, Hongzhi Yin, Jundong Li, Qinyong Wang, Nguyen Quoc Viet Hung, and Xiangliang Zhang. Self-supervised multi-channel hypergraph convolutional network for social recommendation. In Proceedings of the 30th International Conference on World Wide Web, pages 413–424, 2021.
[32] Xin Wang, Wei Lu, Martin Ester, Can Wang, and Chun Chen. Social recommendation with strong and weak ties. In Proceedings of the 25th ACM Conference on Information and Knowledge Management, pages 5–14, 2016.
[33] Chuxu Zhang, Lu Yu, Yan Wang, Chirag Shah, and Xiangliang Zhang. Collaborative user network embedding for social recommender systems. In Proceedings of the 2017 SIAM International Conference on Data Mining, pages 381–389, 2017.
[34] Le Wu, Peijie Sun, Yanjie Fu, Richang Hong, Xiting Wang, and Meng Wang. A neural influence diffusion model for social recommendation. In Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 235–244, 2019.

校內：2027-08-24公開
校外：2027-08-24公開電子論文尚未授權公開，紙本請查館藏目錄

簡易檢索 / 詳目顯示

相關論文