臺灣博碩士論文加值系統

近年來由於龐大的資料量，電子商務的商品推薦變成一項具有挑戰性的工作。因此，我們使用了異質性資訊網路表示法學習（Heterogeneous Information Network Embedding），能夠將網路上不同類型的節點及之間的關係投影到低維度向量空間，以進行電子商務相關的產品推薦工作。本論文提出了一個基於異質性資訊網路表示法學習的電子商務推薦系統，能夠更有效地整合額外資訊（Meta Information）。首先，我們萃取標題的詞彙並與商品鏈結，再加入使用者過去的歷史紀錄轉換成異質性資訊網路。從這個網路中，我們可以使用各式各樣的網路表示法學習方法訓練，並在同一個向量空間中學習使用者及商品的表示式。除此之外，我們更將學習到的表示法當做特徵值，結合矩陣分解（Matrix Factorization）及排序學習（Learning to Rank）的做法，來達到有效地推薦商品的目的。在實際電商~Amazon~的資料集中，此論文的方法能使推薦的效果有所提升。另外，此方法也能夠有效改善電子商務推薦系統所重視的覆蓋率（Coverage）表現。

In recent years, E-commerce product recommendation has been a challenging task due to its data sparsity and volume. Heterogeneous information network embedding encodes the node information into low-dimensions vector space from different types of nodes and their corresponding relations. In this paper, we propose an E-commerce product recommendation method based on the heterogeneous network embedding. First, we incorporate words from product title as the attributes of the item. Then, we transform words, and user behavior into heterogeneous network for E-commerce. For this network, we use various network embedding methods to learn both user and item representations in the same latent space. Moreover, we integrate the learned embedding as the features into Matrix Factorization and Learning to Rank. The experiment results show that we improve the recommendation quality on Amazon dataset. Also, we demonstrate our model can perform better in terms of coverage, the focus of E-commerce recommendation systems.

致謝 1
中文摘要 2
Abstract 3
第一章 緒論 1
第二章 相關文獻探討 4
2.1 推薦系統 4
2.2 網路表示法學習 5
第三章 研究方法 7
3.1 問題定義 7
3.2 異質性資訊網路表示法學習 8
3.2.1 建圖策略 8
3.2.1 Deepwalk 9
3.2.1 LINE 10
3.2.1 HPE 11
3.2.1 metapath2vec 12
3.3 推薦系統 13
第四章 實驗結果與討論 15
4.1 資料集 15
4.2 實驗設定 16
4.3 評估標準 18
4.4 實驗結果 18
4.4.1 準確率及召回率表現 18
4.4.2 覆蓋率表現 20
4.4.3 建圖策略比較 22
4.4.4 案例分析-網路表示法學習 22
4.4.5 案例分析-推薦系統 25
第五章 結論 27

[1] Paul Resnick, Neophytos Iacovou, Mitesh Suchak, Peter Bergstrom, and John Riedl. Grouplens: An open architecture for collaborative filtering of netnews. In Proceed- ings of the 1994 ACM Conference on Computer Supported Cooperative Work, CSCW ’94, pages 175–186. ACM, 1994.
[2] Michael J. Pazzani and Daniel Billsus. The adaptive web. chapter Content-based Recommendation Systems, pages 325–341. Springer-Verlag, 2007.
[3] Robin Burke. Hybrid recommender systems: Survey and experiments. User Model- ing and User-Adapted Interaction, 12(4):331–370, November 2002.
[4] Yoshua Bengio, Aaron Courville, and Pascal Vincent. Representation learning: A review and new perspectives. IEEE transactions on pattern analysis and machine intelligence, 35(8):1798–1828, 2013.
[5] Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg Corrado, and Jeffrey Dean. Dis- tributed representations of words and phrases and their compositionality. In Pro- ceedings of the 26th International Conference on Neural Information Processing Systems - Volume 2, NIPS’13, pages 3111–3119. Curran Associates Inc., 2013.
[6] Bryan Perozzi, Rami Al-Rfou, and Steven Skiena. Deepwalk: Online learning of social representations. In Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’14, pages 701–710. ACM, 2014.
[7] Jian Tang, Meng Qu, Mingzhe Wang, Ming Zhang, Jun Yan, and Qiaozhu Mei.Line: Large-scale information network embedding. In WWW. ACM, 2015.
[8] Aditya Grover and Jure Leskovec. Node2vec: Scalable feature learning for networks. In Proceedings of the 22Nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’16, pages 855–864. ACM, 2016.
[9] Yehuda Koren, Robert Bell, and Chris Volinsky. Matrix factorization techniques for recommender systems. Computer, 42(8), 2009.
[10] Guang Ling, Michael R Lyu, and Irwin King. Ratings meet reviews, a combined ap- proach to recommend. In Proceedings of the 8th ACM Conference on Recommender systems, pages 105–112. ACM, 2014.
[11] Julian McAuley and Jure Leskovec. Hidden factors and hidden topics:Understanding rating dimensions with review text. In Proceedings of the 7th ACM Conference on Recommender Systems, RecSys ’13, pages 165–172. ACM, 2013.
[12] Wei Zhang, Quan Yuan, Jiawei Han, and Jianyong Wang. Collaborative multi- level embedding learning from reviews for rating prediction. In Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, IJCAI’16, pages 2986–2992. AAAI Press, 2016.
[13] Julian McAuley, Christopher Targett, Qinfeng Shi, and Anton Van Den Hengel. Image-based recommendations on styles and substitutes. In Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 43–52. ACM, 2015.
[14] Ruining He and Julian McAuley. Vbpr: Visual bayesian personalized ranking from implicit feedback. 2016.
[15] 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. International World Wide Web Conferences Steering Committee, 2016.
[16] Xiangnan He, Lizi Liao, Hanwang Zhang, Liqiang Nie, Xia Hu, and Tat-Seng Chua. Neural collaborative filtering. In Proceedings of the 26th International Conference on World Wide Web, WWW ’17, pages 173–182. International World Wide Web Conferences Steering Committee, 2017.
[17] Lei Zheng, Vahid Noroozi, and Philip S. Yu. Joint deep modeling of users and items using reviews for recommendation. In Proceedings of the Tenth ACM International Conference on Web Search and Data Mining, WSDM ’17, pages 425–434. ACM, 2017.
[18] Yongfeng Zhang, Qingyao Ai, Xu Chen, and W Bruce Croft. Joint representa- tion learning for top-n recommendation with heterogeneous information sources. In Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, pages 1449–1458. ACM, 2017.
[19] Chuan Shi, Binbin Hu, Wayne Xin Zhao, and Philip S Yu. Heterogeneous information network embedding for recommendation. arXiv preprint arXiv:1711.10730, 2017.
[20] ChengYang,ZhiyuanLiu,DeliZhao,MaosongSun,andEdwardY.Chang.Network representation learning with rich text information. In Proceedings of the 24th Inter- national Conference on Artificial Intelligence, IJCAI’15, pages 2111–2117. AAAI Press, 2015.
[21] Cunchao Tu, Weicheng Zhang, Zhiyuan Liu, and Maosong Sun. Max-margin deep- walk: Discriminative learning of network representation. In Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, IJCAI’16, pages 3889–3895. AAAI Press, 2016.
[22] Shiyu Chang, Wei Han, Jiliang Tang, Guo-Jun Qi, Charu C. Aggarwal, and Thomas S. Huang. Heterogeneous network embedding via deep architectures. In Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’15, pages 119–128. ACM, 2015.
[23] Yuxiao Dong, Nitesh V. Chawla, and Ananthram Swami. Metapath2vec: Scalable representation learning for heterogeneous networks. In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’17, pages 135–144. ACM, 2017.
[24] Chih-Ming Chen, Ming-Feng Tsai, Yu-Ching Lin, and Yi-Hsuan Yang. Query-based music recommendations via preference embedding. In Proceedings of the 10th ACM Conference on Recommender Systems, RecSys ’16, pages 79–82. ACM, 2016.
[25] Kuan Liu and Prem Natarajan. Wmrb: Learning to rank in a scalable batch training approach. arXiv preprint arXiv:1711.04015, 2017.
[26] 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, UAI ’09, pages 452–461. AUAI Press, 2009.
[27] Jason Weston, Samy Bengio, and Nicolas Usunier. Wsabie: Scaling up to large vocabulary image annotation. In Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence - Volume Volume Three, IJCAI’11, pages 2764–2770. AAAI Press, 2011.
[28] Chih-Ming Chen, Yi-Hsuan Yang, Yian Chen, and Ming-Feng Tsai. Vertex-context sampling for weighted network embedding. arXiv preprint arXiv:1711.00227, 2017.
[29] Maciej Kula. Metadata embeddings for user and item cold-start recommendations. In Toine Bogers and Marijn Koolen, editors, Proceedings of the 2nd Workshop on New Trends on Content-Based Recommender Systems co-located with 9th ACM Conference on Recommender Systems (RecSys 2015), Vienna, Austria, September 16-20, 2015., volume 1448 of CEUR Workshop Proceedings, pages 14–21. CEUR- WS.org, 2015.
[30] Laurens van der Maaten and Geoffrey Hinton. Visualizing data using t-sne. Journal of machine learning research, 9(Nov):2579–2605, 2008.