基于TCN的短期兴趣个性化序列推荐
TCN-Based Short Term Interest Personalized Sequence Recommendation
摘要: 随着移动互联网蓬勃发展，个性化推荐也迎来了新的机遇和挑战。传统推荐算法更注重静态长期特征的推荐，但手机淘宝、抖音等feed流沉浸式应用中，长时间的快速变换的浏览行为，需要更快的计算方法捕捉兴趣的频繁变化。本文提出一种基于TCN的兴趣序列推荐算法，通过水平和垂直两个方向上卷积，捕获用户的短期动态兴趣信息，再结合用户长期兴趣信息，完成推荐。实验结果表明，与其他推荐算法相比，R-TCN (Rcommendation-TCN)的Top-N推荐效果更好，训练时间更快，更能捕获短期兴趣变化，适合用于并行处理的工业推荐环境。
Abstract: With the rapid development of mobile Internet, personalized recommendation also faces new opportunities and challenges. Traditional recommendation algorithms pay more attention to static long-term feature recommendation, but in Mobile Taobao, Douying and other feed flow immersive applications, long-term fast changing browsing behavior requires faster calculation methods to capture frequent changes in interest. In this paper, a TCN-based interest sequence recommendation algorithm is proposed. By convolution in horizontal and vertical directions, the short-term dynamic interest information of users is captured, and then the long-term interest information of users is combined to complete the recommendation. The experimental results show that compared with other recommendation algorithms, R-TCN (Recommendation-TCN) has better performance in Top-N recommendation, faster training time, better ability to capture short-term interest changes, and is suitable for parallel processing industry recommendation environment.
文章引用：许亮, 牛少彰. 基于TCN的短期兴趣个性化序列推荐[J]. 计算机科学与应用, 2019, 9(11): 2161-2173. https://doi.org/10.12677/CSA.2019.911242

参考文献

[1] Zhang, W., Du, T. and Wang, J. (2016) Deep Learning over Multi-Field Categorical Data. In: Ferro, N., et al., Eds., Ad-vances in Information Retrieval. ECIR 2016. Lecture Notes in Computer Science, Springer, Cham, 45-57. [Google Scholar] [CrossRef] 
[2] Qu, Y., Fang, B., Zhang, W., et al. (2018) Product-Based Neu-ral Networks for User Response Prediction over Multi-Field Categorical Data. ACM Transactions on Information Sys-tems, 37, Article No. 5. [Google Scholar] [CrossRef] 
[3] Cheng, H.T., Koc, L., Harmsen, J., et al. (2016) Wide & Deep Learning for Recommender Systems. Proceedings of the 1st Workshop on Deep Learning for Recommender Systems, Boston, MA, 15 September 2016, 7-10. [Google Scholar] [CrossRef] 
[4] Guo, H., Tang, R., Ye, Y., et al. (2017) DeepFM: A Factoriza-tion-Machine Based Neural Network for CTR Prediction. Proceedings of the Twenty-Sixth International Joint Confer-ence on Artificial Intelligence, Melbourne, Australia, 19-25 August 2017, 1725-1731. [Google Scholar] [CrossRef] 
[5] Wang, R., Fu, B., Fu, G. and Wang, M.L. (2017) Deep & Cross Net-work for Ad Click Predictions. Proceedings of the ADKDD’17, Halifax, 14 August 2017, 1-7. [Google Scholar] [CrossRef] 
[6] Zhou, G., Song, C., Zhu, X., et al. (2017) Deep Interest Network for Click-Through Rate Prediction. Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, London, United Kingdom, 19-23 August 2018, 1059-1068. [Google Scholar] [CrossRef] 
[7] Cheng, C., Yang, H.Q., Lyu, M.R. and King, I. (2013) Where You Like to Go Next: Successive Point-of-Interest Recommendation. Proceedings of the 23rd International Joint Conference on Artificial Intelligence, Beijing, China, 3-9 August 2013, 2605-2611.
[8] He, R. and McAuley, J. (2016) Fusing Similarity Models with Markov Chains for Sparse Sequential Recommendation. 2016 IEEE 16th International Confer-ence on Data Mining, Barcelona, Spain, 12-15 December 2016, 191-200. [Google Scholar] [CrossRef] 
[9] Rendle, S., Freudenthaler, C. and Schmidt-Thieme, L. (2010) Fac-torizing Personalized Markov Chains for Next-Basket Recommendation. In: Proceedings of International Conference on World Wide Web, ACM, New York, 811-820. [Google Scholar] [CrossRef] 
[10] Wang, P.F., Guo, J.F., Lan, Y.Y., Xu, J., Wan, S.X. and Cheng, X.Q. (2015) Learning Hierarchical Representation Model for Next Basket Recommendation. In: Proceedings of Interna-tional ACM SIGIR Conference on Research and Development in Information Retrieval, ACM, New York, 403-412. [Google Scholar] [CrossRef] 
[11] Bai, S., Kolter, J.Z. and Koltun, V. (2018) An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling.
[12] Vo, N. and Hays, J. (2018) Generali-zation in Metric Learning: Should the Embedding Layer Be the Embedding Layer? 2019 IEEE Winter Conference on Ap-plications of Computer Vision, Waikoloa Village, HI, 7-11 January 2019, 589-598. [Google Scholar] [CrossRef] 
[13] Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R. and Li, F.-F. (2014) Large-Scale Video Classification with Convolutional Neural Networks. 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, 23-28 June 2014, 1725-1732. [Google Scholar] [CrossRef] 
[14] Krizhevsky, A., Sutskever, I. and Hinton, G.E. (2012) ImageNet Classification with Deep Convolutional Neural Networks. In: Advances in Neural Information Processing Systems, 1097-1105.
[15] Kim, Y. (2014) Convolutional Neural Networks for Sentence Classification. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, Doha, Qatar, October 2014, 1756-1751. [Google Scholar] [CrossRef] 
[16] Szegedy, C., Ioffe, S., Vanhoucke, V., et al. (2016) Inception-v4, Incep-tion-ResNet and the Impact of Residual Connections on Learning.
[17] Brazil, T.J. (1995) Causal-Convolution-A New Method for the Transient Analysis of Linear Systems at Microwave Frequencies. IEEE Transactions on Microwave Theory & Techniques, 43, 315-323. [Google Scholar] [CrossRef] 
[18] Oord, A.V.D., Dieleman, S., Zen, H., et al. (2016) WaveNet: A Generative Model for Raw Au-dio.
[19] https://grouplens.org/datasets/movielens/20m/
[20] http://jmcauley.ucsd.edu/data/amazon/
[21] Pan, R., Zhou, Y.H., Cao, B., Liu, N.N., Lukose, R., Scholz, M. and Yang, Q. (2008) One-Class Collaborative Filtering. 2008 Eighth IEEE International Conference on Data Mining, Pisa, Italy, 15-19 December 2008, 502-511. [Google Scholar] [CrossRef]