請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/85220完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 鄭卜壬(Pu-Jen Cheng) | |
| dc.contributor.author | Pin-Hsin Hsiao | en |
| dc.contributor.author | 蕭品新 | zh_TW |
| dc.date.accessioned | 2023-03-19T22:51:05Z | - |
| dc.date.copyright | 2022-08-10 | |
| dc.date.issued | 2022 | |
| dc.date.submitted | 2022-08-03 | |
| dc.identifier.citation | [1] S. Amer-Yahia, S. B. Roy, A. Chawlat, G. Das, and C. Yu. Group recommendation: Semantics and efficiency. Proc. VLDB Endow., page 754–765, 2009. [2] M. L. Babak Loni, Roberto Pagano and A. Hanjalic. Bayesian personalized ranking with multi-channel user feedback. In RecSys, page 361–364, 2016. [3] J. K. Badrul Sarwar, George Karypis and J. Riedl. Item-based collaborative filtering recommendation algorithms. In WWW, page 285–295, 2001. [4] L. Baltrunas, T. Makcinskas, and F. Ricci. Group recommendations with rank aggregation and collaborative filtering. In RecSys, page 119–126, 2010. [5] S. Berkovsky and J. Freyne. Group-based recipe recommendations: Analysis of data aggregation strategies. In RecSys, page 111–118, 2010. [6] X. H. D. J. Bowen Jin, Chen Gao and Y. Li. Multi-behavior recommendation with graph convolutional networks. In SIGIR, pages 659–668, 2020. [7] D. Cao, X. He, L. Miao, Y. An, C. Yang, and R. Hong. Attentive group recommendation. In SIGIR, pages 645–654, 2018. [8] Y. Cao, X. Wang, X. He, Z. Hu, and T.-S. Chua. Unifying knowledge graph learning and recommendation: Towards a better understanding of user preferences. In WWW, page 151–161, 2019. [9] D. G. X. C. F. F. Y. L. T. C. Chen Gao, Xiangnan He and D. Jin. Neural multi-task recommendation from multi-behavior data. In ICDE, pages 1554–1557, 2019. [10] H.-T. Cheng, L. Koc, J. Harmsen, T. Shaked, T. Chandra, H. Aradhye, G. Anderson, G. Corrado, W. Chai, M. Ispir, R. Anil, Z. Haque, L. Hong, V. Jain, X. Liu, and H. Shah. Wide & deep learning for recommender systems. In DLRS, page 7–10, 2016. [11] X. Guan, Z. Cheng, X. He, Y. Zhang, Z. Zhu, Q. Peng, and T.-S. Chua. Attentive aspect modeling for review-aware recommendation. In ACM Trans. Inf. Syst., page 27, 2019. [12] H. Guo, R. Tang, Y. Ye, Z. Li, and X. He. Deepfm: A factorization-machine based neural network for ctr prediction. In IJCAI, page 1725–1731, 2017. [13] W. L. X. H. H. L. H. Zhang, F. Shen and T.-S. Chua. Discrete collaborative fltering. In SIGIR, page 325–334, 2016. [14] X. He and T.-S. Chua. Neural factorization machines for sparse predictive analytics. In SIGIR, page 355–364, 2017. [15] T. N. Kipf and M. Welling. Semi-supervised classification with graph convolutional networks. In ICLR, 2017. [16] W. Krichene and S. Rendle. On sampled metrics for item recommendation. In SIGKDD, page 1748–1757, 2020. [17] R. C. L. L. S. T. K. C. P. Z. B. Liu, Q.; Xie and L. Lin. Graph neural network for tag ranking in tag-enhanced video recommendation. In CIKM, page 2613–2620, 2020. [18] J. Ma, C. Zhou, P. Cui, H. Yang, and W. Zhu. Learning disentangled representations for recommendation. In NeurlIPS, 2019. [19] X. Ning and G. Karypis. Slim: Sparse linear methods for top-n recommender systems. In ICDM, page 497–506, 2011. [20] S. Rendle. Factorization machines. In ICDM, pages 995–1000, 2010. [21] S. Sajjadi Ghaemmaghami and A. Salehi-Abari. Deepgroup: Group recommendation with implicit feedback. In CIKM, page 3408–3412, 2021. [22] A. Sankar, Y. Wu, Y. Wu, W. Zhang, H. Yang, and H. Sundaram. Groupim: A mutual information maximization framework for neural group recommendation. In SIGIR, pages 1279–1288, 2020. [23] X. N. Santosh Kabbur and G. Karypis. Fism: factored item similarity models for top-n recommender systems. In SIGKDD, page 659–667, 2013. [24] H. Wang, B. Chen, and W.-J. Li. Collaborative topic regression with social regularization for tag recommendation. In IJCAI, page 2719–2725, 2013. [25] X. Wang, H. Jin, A. Zhang, X. He, T. Xu, and T.-S. Chua. Disentangled graph collaborative filtering. In SIGIR, page 1001–1010, 2020. [26] M. Y. K. X. He, H. Zhang and T.-S. Chua. Fast matrix factorization for online recommendation with implicit feedback. In SIGIR, page 549–558, 2016. [27] R. B. Yehuda Koren and C. Volinsky. Matrix factorization techniques for recommender systems. In Computer, page 8, 2009. [28] T.-C. C. Yu-Ta Lu, Shoou-I Yu and J. Y. jen Hsu. A content-based method to enhance tag recommendation. In ICJAI, page 2064–2069, 2009. [29] F. Zhang, N. J. Yuan, D. Lian, X. Xie, and W.-Y. Ma. Collaborative knowledge base embedding for recommender systems. In SIGKDD, page 353–362, 2016. [30] Y. Zhang, Q. Ai, X. Chen, and W. B. Croft. Joint representation learning for top-n recommendation with heterogeneous information sources. In CIKM, page 1449–1458, 2017. [31] Y. Zhang, Z. Zhu, Y. He, and J. Caverlee. Content-collaborative disentanglement representation learning for enhanced recommendation. In RecSys, page 43–52, 2020. [32] C.-Y. C. Zhixiang He and J.-D. Zhang. Game: Learning graphical and attentive multi-view embeddings for occasional group recommendation. In SIGIR, page 649–658, 2020. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/85220 | - |
| dc.description.abstract | 推薦系統對現代社會產生了重大影響，從根本上改變了人們的消費習慣，而分析用戶行為是推薦系統研究領域中最熱門的議題之一，利用用戶的歷史互動資料來了解、分析用戶的行為，可以提升推薦系統的準確度。以往的研究主要集中在分析單個用戶的行為，獲取更多隱含訊息，或者尋找有相似行為的用戶來提高推薦的表現。然而，人們傾向於一起做出購買決定，例如，當和朋友去看電影時，我們通常會根據我們的共同興趣來決定看哪部電影。為了讓推薦系統有更進一步的正確率，找到使用者的共同興趣將是一個關鍵的問題。一個簡單找到使用者共同興趣的方法是直接取每個用戶行為的交集，然而這樣每個用戶行為中的潛在行為將被忽略，且共同興趣的可解釋性將受到限制。 為了更好地模擬每個用戶與項目交互和共同興趣的行為，我們提出了共同興趣（COIN）模型來尋找這項工作中的共同興趣。COIN 模型利用 Graph Convolution Network 的特性對 user-item 交互圖中的高階特徵（high-order) 進行建模，並利用 item 標籤屬性進行解釋。最後，在三個真實世界數據集上的大量實驗結果顯示了我們的 COIN 模型與其他方法相比的有效性。 | zh_TW |
| dc.description.abstract | Recommender systems have a significant impact on human society, and it has changed people’s consumption habits. Analyzing user behavior is one of the most popular topics among the recommendation research field. Previous studies focused on either analyzing the behavior of a single user, obtaining more implicit information, or finding similar users to enhance recommendation performance. However, people tend to make purchase decisions together, e.g., when going to the movies with friends, we usually decide which movie to watch based on our common interests. In order to have further improvement in recommendation, finding common interests will be a critical problem. A simple way to find common interests is to directly take the intersection of each user’s behavior. However, the latent semantics within the behavior of each user will be ignored, and the explainability of common interests will be limited. To better model the behavior of each user with item interaction and common interest, we propose the COmmon INterest (COIN) model for finding the common interests in this work. The COIN model leverages the characteristics of Graph Convolution Network to model high-order features in the user-item interaction graph and make use of the item tag attribute for the explanation. Lastly, extensive experimental results on three real-world datasets show the effectiveness of our COIN model compared with baseline methods. | en |
| dc.description.provenance | Made available in DSpace on 2023-03-19T22:51:05Z (GMT). No. of bitstreams: 1 U0001-2407202221292000.pdf: 2056468 bytes, checksum: b60986b680ff13b9e0d91f8cf14c4f94 (MD5) Previous issue date: 2022 | en |
| dc.description.tableofcontents | Acknowledgements ii 摘要 iv Abstract v Contents vii List of Figures ix List of Tables x Chapter 1 Introduction 1 Chapter 2 Related Work 4 2.1 Disentangled Recommendation 4 2.2 Group Recommendation 5 2.3 Attribute-Aware Recommendation 5 2.3.1 Click Through Rate 6 2.3.2 Top-N Recommendation 6 Chapter 3 Proposed Method 7 3.1 Methodology 7 3.1.1 Problem Formulation 7 3.1.2 Tag Attribute Encoder 8 3.1.3 Light Propagation on Graph 8 3.1.3.1 Light Propagation 8 3.1.3.2 Matrix Form 9 3.1.3.3 Output 10 3.1.4 User Clustering 10 3.1.5 Tag Attribute Decoder 11 3.1.6 Training 12 3.1.7 Inference 13 Chapter 4 Experiments 14 4.1 Experimental Settings 14 4.1.1 Dataset Description 14 4.1.2 Evaluation 15 4.1.3 Compared Methods 15 4.2 Analysis of results 16 4.3 Ablation Study 18 4.4 Layer Impact 19 4.5 Group Impact 21 Chapter 5 Conclusions 23 5.1 Conclusions 23 5.2 Future Work 23 References 25 | |
| dc.language.iso | en | |
| dc.subject | 可解釋性 | zh_TW |
| dc.subject | 推薦系統 | zh_TW |
| dc.subject | 使用者行為 | zh_TW |
| dc.subject | 圖卷積網路 | zh_TW |
| dc.subject | Graph Convolutional Network | en |
| dc.subject | Explanation | en |
| dc.subject | User Behavior | en |
| dc.subject | Recommendation | en |
| dc.title | 基於圖卷積網路探討推薦系統中使用者之共同興趣 | zh_TW |
| dc.title | COIN: Learning User Common Interests for Unseen Group Recommendation | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 110-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 陳信希(Hsin-Hsi Chen),陳柏琳(Berlin Chen),馬偉雲(Wei-Yun Ma),姜俊宇(Jyun-Yu Jiang) | |
| dc.subject.keyword | 推薦系統,使用者行為,圖卷積網路,可解釋性, | zh_TW |
| dc.subject.keyword | Recommendation,User Behavior,Graph Convolutional Network,Explanation, | en |
| dc.relation.page | 28 | |
| dc.identifier.doi | 10.6342/NTU202201679 | |
| dc.rights.note | 同意授權(限校園內公開) | |
| dc.date.accepted | 2022-08-03 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 資訊網路與多媒體研究所 | zh_TW |
| dc.date.embargo-lift | 2022-08-10 | - |
| 顯示於系所單位： | 資訊網路與多媒體研究所 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| U0001-2407202221292000.pdf 授權僅限NTU校內IP使用（校園外請利用VPN校外連線服務） | 2.01 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。