研究生: |
Goksucan Erkoc Goksucan Erkoc |
---|---|
論文名稱: |
推薦系統之序列預測模型的時間嵌入特徵研究 A Study of Temporal Embeddings for Sequence Prediction Model of Recommendation Systems |
指導教授: |
林伯慎
Bor-Shen Lin |
口試委員: |
林伯慎
Bor-Shen Lin 楊傳凱 Chuan-kai Yang 羅乃維 Nai-Wei Lo |
學位類別: |
碩士 Master |
系所名稱: |
管理學院 - 資訊管理系 Department of Information Management |
論文出版年: | 2022 |
畢業學年度: | 110 |
語文別: | 英文 |
論文頁數: | 62 |
外文關鍵詞: | time intervals, position embedding, temporal embedding, social time embeddings, sequential recommendation |
相關次數: | 點閱:149 下載:3 |
分享至: |
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 |
Sequential recommendation is one of the hottest topics in the recommendation system field. Recently there are several improvements on this topic. Notably, thanks to natural language processing, many technics have started to be implemented in the sequential recommendation field, such as transformers and token embedding. The nature of the recommendation is although relevant to natural language but not the same. To improve the prediction performance, a few works try to make use of side information such as temporal information or attributes of the items in the sequence. In this thesis, the effects of token embeddings and various temporal embeddings such as position embeddings, and time interval embeddings are first investigated. Additionally, three types of social time embeddings, named as month, day and hour, are proposed to model the change of user behavior with respect to season, day of week, and time of day, respectively. Experiments were conducted on five databases of movieLens, Steam, Amazon beauty, Amazon clothing & jewelry and Gowalla, and the results show that both position and time interval embeddings can contribute to the online transaction services of MovieLens and Steam. Moreover, social time embeddings are effective for all the databases, and more improvements can be achieved for online shopping services of Amazon beauty, Amazon clothing& jewelry.
[1] P. G. Roetzel, “Information overload in the information age: a review of the literature from business administration, business psychology, and related disciplines with a bibliometric approach and framework development,” Bus. Res., vol. 12, no. 2, pp. 479–522, Dec. 2019, doi: 10.1007/s40685-018-0069-z.
[2] F. Ricci, L. Rokach, and B. Shapira, Eds., Recommender Systems Handbook. New York, NY: Springer US, 2022. doi: 10.1007/978-1-0716-2197-4.
[3] G. Jawaheer, M. Szomszor, and P. Kostkova, “Comparison of implicit and explicit feedback from an online music recommendation service,” in Proceedings of the 1st International Workshop on Information Heterogeneity and Fusion in Recommender Systems - HetRec ’10, Barcelona, Spain, 2010, pp. 47–51. doi: 10.1145/1869446.1869453.
[4] D. Jannach, L. Lerche, and M. Zanker, “Recommending Based on Implicit Feedback,” in Social Information Access, vol. 10100, P. Brusilovsky and D. He, Eds. Cham: Springer International Publishing, 2018, pp. 510–569. doi: 10.1007/978-3-319-90092-6_14.
[5] Z. Meng, R. McCreadie, C. Macdonald, and I. Ounis, “Exploring Data Splitting Strategies for the Evaluation of Recommendation Models,” in Fourteenth ACM Conference on Recommender Systems, Virtual Event Brazil, Sep. 2020, pp. 681–686. doi: 10.1145/3383313.3418479.
[6] C. C. Aggarwal, Recommender Systems. Cham: Springer International Publishing, 2016. doi: 10.1007/978-3-319-29659-3.
[7] Y. Koren, R. Bell, and C. Volinsky, “Matrix Factorization Techniques for Recommender Systems,” Computer, vol. 42, no. 8, pp. 30–37, Aug. 2009, doi: 10.1109/MC.2009.263.
[8] H. Fang, G. Guo, D. Zhang, and Y. Shu, “Deep Learning-Based Sequential Recommender Systems: Concepts, Algorithms, and Evaluations,” in Web Engineering, vol. 11496, M. Bakaev, F. Frasincar, and I.-Y. Ko, Eds. Cham: Springer International Publishing, 2019, pp. 574–577. doi: 10.1007/978-3-030-19274-7_47.
[9] H. Fang, D. Zhang, Y. Shu, and G. Guo, “Deep Learning for Sequential Recommendation: Algorithms, Influential Factors, and Evaluations.” arXiv, Oct. 10, 2020. Accessed: Jun. 11, 2022. [Online]. Available: http://arxiv.org/abs/1905.01997
[10] S. Kotsiantis and D. Kanellopoulos, “Association Rules Mining: A Recent Overview,” p. 12.
[11] G. Sottocornola, P. Symeonidis, and M. Zanker, “Session-based News Recommendations,” in Companion of the The Web Conference 2018 on The Web Conference 2018 - WWW ’18, Lyon, France, 2018, pp. 1395–1399. doi: 10.1145/3184558.3191582.
[12] S. Rendle, C. Freudenthaler, and L. Schmidt-Thieme, “Factorizing personalized Markov chains for next-basket recommendation,” in Proceedings of the 19th international conference on World wide web - WWW ’10, Raleigh, North Carolina, USA, 2010, p. 811. doi: 10.1145/1772690.1772773.
[13] R. He and J. McAuley, “Fusing Similarity Models with Markov Chains for Sparse Sequential Recommendation,” in 2016 IEEE 16th International Conference on Data Mining (ICDM), Dec. 2016, pp. 191–200. doi: 10.1109/ICDM.2016.0030.
[14] Cheng et al., “Wide & Deep Learning for Recommender Systems.” arXiv, Jun. 24, 2016. Accessed: Sep. 15, 2022. [Online]. Available: http://arxiv.org/abs/1606.07792
[15] J. Tang and K. Wang, “Personalized Top-N Sequential Recommendation via Convolutional Sequence Embedding.” arXiv, Sep. 19, 2018. Accessed: Sep. 15, 2022. [Online]. Available: http://arxiv.org/abs/1809.07426
[16] A. Yan, S. Cheng, W.-C. Kang, M. Wan, and J. McAuley, “CosRec: 2D Convolutional Neural Networks for Sequential Recommendation.” arXiv, Aug. 26, 2019. Accessed: Sep. 15, 2022. [Online]. Available: http://arxiv.org/abs/1908.09972
[17] B. Hidasi, A. Karatzoglou, L. Baltrunas, and D. Tikk, “Session-based Recommendations with Recurrent Neural Networks.” arXiv, Mar. 29, 2016. Accessed: Sep. 15, 2022. [Online]. Available: http://arxiv.org/abs/1511.06939
[18] W.-C. Kang and J. McAuley, “Self-Attentive Sequential Recommendation.” arXiv, Aug. 20, 2018. Accessed: Jun. 01, 2022. [Online]. Available: http://arxiv.org/abs/1808.09781
[19] J. Li, Y. Wang, and J. McAuley, “Time Interval Aware Self-Attention for Sequential Recommendation,” in Proceedings of the 13th International Conference on Web Search and Data Mining, Houston TX USA, Jan. 2020, pp. 322–330. doi: 10.1145/3336191.3371786.
[20] S. M. Cho, E. Park, and S. Yoo, “MEANTIME: Mixture of Attention Mechanisms with Multi-temporal Embeddings for Sequential Recommendation,” in Fourteenth ACM Conference on Recommender Systems, Sep. 2020, pp. 515–520. doi: 10.1145/3383313.3412216.
[21] J. Seol, Y. Ko, and S. Lee, “Exploiting Session Information in BERT-based Session-aware Sequential Recommendation.” May 19, 2022. doi: 10.1145/3477495.3531910.
[22] D. Bahdanau, K. Cho, and Y. Bengio, “Neural Machine Translation by Jointly Learning to Align and Translate.” arXiv, May 19, 2016. Accessed: Aug. 27, 2022. [Online]. Available: http://arxiv.org/abs/1409.0473
[23] A. Vaswani et al., “Attention Is All You Need.” arXiv, Dec. 05, 2017. Accessed: Sep. 19, 2022. [Online]. Available: http://arxiv.org/abs/1706.03762
[24] Z. Niu, G. Zhong, and H. Yu, “A review on the attention mechanism of deep learning,” Neurocomputing, vol. 452, pp. 48–62, Sep. 2021, doi: 10.1016/j.neucom.2021.03.091.
[25] Z. Fang, “Long- and Short-term Sequential Recommendation with Enhanced Temporal Self-attention,” p. 58.
[26] A. Paszke et al., “PyTorch: An Imperative Style, High-Performance Deep Learning Library,” p. 12.
[27] S. Chetlur et al., “cuDNN: Efficient Primitives for Deep Learning.” arXiv, Dec. 17, 2014. Accessed: Aug. 29, 2022. [Online]. Available: http://arxiv.org/abs/1410.0759
[28] D. Luebke, “CUDA: Scalable parallel programming for high-performance scientific computing,” in 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, May 2008, pp. 836–838. doi: 10.1109/ISBI.2008.4541126.
[29] F. M. Harper and J. A. Konstan, “The MovieLens Datasets: History and Context,” ACM Trans. Interact. Intell. Syst., vol. 5, no. 4, pp. 1–19, Jan. 2016, doi: 10.1145/2827872.
[30] “MovieLens.” https://movielens.org/ (accessed Aug. 27, 2022).
[31] M. Wan and J. McAuley, “Item recommendation on monotonic behavior chains,” in Proceedings of the 12th ACM Conference on Recommender Systems, Vancouver British Columbia Canada, Sep. 2018, pp. 86–94. doi: 10.1145/3240323.3240369.
[32] A. Pathak, K. Gupta, and J. McAuley, “Generating and Personalizing Bundle Recommendations on Steam,” in Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval, Shinjuku Tokyo Japan, Aug. 2017, pp. 1073–1076. doi: 10.1145/3077136.3080724.
[33] R. He and J. 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, Montréal Québec Canada, Apr. 2016, pp. 507–517. doi: 10.1145/2872427.2883037.
[34] J. McAuley, C. Targett, Q. Shi, and A. 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, Santiago Chile, Aug. 2015, pp. 43–52. doi: 10.1145/2766462.2767755.
[35] E. Cho, S. A. Myers, and J. Leskovec, “Friendship and mobility: user movement in location-based social networks,” in Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining - KDD ’11, San Diego, California, USA, 2011, p. 1082. doi: 10.1145/2020408.2020579.
[36] T. Silveira, M. Zhang, X. Lin, Y. Liu, and S. Ma, “How good your recommender system is? A survey on evaluations in recommendation,” Int. J. Mach. Learn. Cybern., vol. 10, no. 5, pp. 813–831, May 2019, doi: 10.1007/s13042-017-0762-9.