Abstract
Traditional matrix factorization techniques for recommendation have a basic assumption that user interests will not change over time, which is not consistent with the reality. To this end, temporal user-item interaction sequences are important to capture users’ dynamic interests towards more accurate and timely recommendation. Previous works used to capture dynamic interests based on the basic recurrent neural networks. However, they do not distinguish the static interests which reflect user’s long-term preferences from temporal interests caused by occasional incidents. They also treat all the user’s past temporal interests equally when performing future rating prediction. In this paper, we leverage Probabilistic Matrix Factorization (PMF) to learn both static and temporal interests for users, and design a new filtering layer to adaptively feed the static and temporal user information to RNN at different time step. We also apply item-dependent attention mechanism to discriminate the importance of different temporal interactions. We conduct extensive experiments to evaluate the performance of our proposed temporal rating prediction method named TRPN. The results show that TRPN can achieve higher performance than several state-of-the-art methods.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. CoRR abs/1409.0473 (2014)
Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: EMNLP, pp. 1724–1734 (2014)
Chung, J., Ahn, S., Bengio, Y.: Hierarchical multiscale recurrent neural networks. CoRR abs/1609.01704 (2016)
Du, Y., Xu, C., Tao, D.: Privileged matrix factorization for collaborative filtering. In: IJCAI, pp. 1610–1616 (2017)
Gao, L., Wu, J., Zhou, C., Hu, Y.: Collaborative dynamic sparse topic regression with user profile evolution for item recommendation. In: AAAI (2017)
He, X., Liao, L., Zhang, H., Nie, L., Hu, X., Chua, T.: Neural collaborative filtering. In: WWW, pp. 173–182 (2017)
He, X., Zhang, H., Kan, M., Chua, T.: Fast matrix factorization for online recommendation with implicit feedback. In: SIGIR, pp. 549–558 (2016)
He, Y., Li, J., Song, Y., He, M., Peng, H.: Time-evolving text classification with deep neural networks. In: Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, IJCAI 2018, pp. 2241–2247 (2018)
Hidasi, B., Karatzoglou, A., Baltrunas, L., Tikk, D.: Session-based recommendations with recurrent neural networks. CoRR abs/1511.06939 (2015)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Huang, X., Wu, L., Chen, E., Zhu, H., Liu, Q., Wang, Y.: Incremental matrix factorization: a linear feature transformation perspective. In: IJCAI (2017)
Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. CoRR abs/1412.6980 (2014)
Koren, Y.: Collaborative filtering with temporal dynamics. In: SIGKDD (2009)
Koren, Y., Bell, R.M., Volinsky, C.: Matrix factorization techniques for recommender systems. IEEE Comput. 42(8), 30–37 (2009)
Lian, D., Zhang, Z., Ge, Y., Zhang, F., Yuan, N.J., Xie, X.: Regularized content-aware tensor factorization meets temporal-aware location recommendation. In: ICDM, pp. 1029–1034 (2016)
Lu, Z., Pan, S.J., Li, Y., Jiang, J., Yang, Q.: Collaborative evolution for user profiling in recommender systems. In: IJCAI, pp. 3804–3810 (2016)
Ruder, S.: An overview of gradient descent optimization algorithms. arXiv preprint arXiv:1609.04747 (2016)
Salakhutdinov, R., Mnih, A.: Probabilistic matrix factorization. In: NIPS (2007)
Sarwar, B.M., Karypis, G., Konstan, J.A., Riedl, J.: Item-based collaborative filtering recommendation algorithms. In: WWW, pp. 285–295 (2001)
Song, Y., Elkahky, A.M., He, X.: Multi-rate deep learning for temporal recommendation. In: SIGIR, pp. 909–912 (2016)
Wang, Q., Yin, H., Hu, Z., Lian, D., Wang, H., Huang, Z.: Neural memory streaming recommender networks with adversarial training. In: KDD (2018)
Wang, W., Yin, H., Du, X., Nguyen, Q.V.H., Zhou, X.: TPM: a temporal personalized model for spatial item recommendation. TIST 9(6), 61:1–61:25 (2018)
Wang, W., Yin, H., Huang, Z., Wang, Q., Du, X., Nguyen, Q.V.H.: Streaming ranking based recommender systems. In: SIGIR, pp. 525–534 (2018)
Wu, C., Ahmed, A., Beutel, A., Smola, A.J., Jing, H.: Recurrent recommender networks. In: WSDM, pp. 495–503 (2017)
Yin, H., Cui, B., Chen, L., Hu, Z., Zhou, X.: Dynamic user modeling in social media systems. ACM Trans. Inf. Syst. 33(3), 10:1–10:44 (2015)
Zhao, L., Lu, Z., Pan, S.J., Yang, Q.: Matrix factorization+ for movie recommendation. In: IJCAI, pp. 3945–3951 (2016)
Acknowledgements
This work is supported by the National Key Research and Development Program of China (No. 2018YFC0831604) and NSFC No. 61602297.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Zhu, H., Shen, Y., Zhou, X. (2019). TRPN: Matrix Factorization Meets Recurrent Neural Network for Temporal Rating Prediction. In: Shao, J., Yiu, M., Toyoda, M., Zhang, D., Wang, W., Cui, B. (eds) Web and Big Data. APWeb-WAIM 2019. Lecture Notes in Computer Science(), vol 11642. Springer, Cham. https://doi.org/10.1007/978-3-030-26075-0_5
Download citation
DOI: https://doi.org/10.1007/978-3-030-26075-0_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-26074-3
Online ISBN: 978-3-030-26075-0
eBook Packages: Computer ScienceComputer Science (R0)