Abstract
Online movie recommender systems aim to address information overload problem in movie perspective. Recently, incorporating knowledge graph into recommender systems as auxiliary information has attracted much attention due to its rich semantic content. In this paper, we propose a deep multi-channel model for dynamic movie recommendation (DMCM), which makes full use of user-item interaction and knowledge graph. First, we learn item embedding, entity embedding and genre embedding from interaction matrix and knowledge graph. Then we design a CNN-based network which can fuse the learnt embeddings and acquire the final movie representation, among which an attention module is applied to better represent the user. Finally, the click-through rate for the user-movie pair is calculated utilizing the obtained user and movie representation. Results of extensive experiments on a real-world dataset show that the proposed DMCM outperforms state-of-art baselines.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Bordes, A., Usunier, N., García-Durán, A., Weston, J., Yakhnenko, O.: Translating embeddings for modeling multi-relational data. In: Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013 (2013)
Harper, F.M., Konstan, J.A.: The MovieLens Datasets: History and Context (2015)
Ji, G., He, S., Xu, L., Kang, L., Zhao, J.: Knowledge graph embedding via dynamic mapping matrix. In: Meeting of the Association for Computational Linguistics & The International Joint Conference on Natural Language Processing (2015)
Lin, Y., Liu, Z., Sun, M., Liu, Y., Zhu, X.: Learning entity and relation embeddings for knowledge graph completion. In: Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence (2015)
Milne, D., Witten, I.H.: Learning to link with wikipedia (2008)
Rendle, S., Freudenthaler, C., Gantner, Z., Schmidt-Thieme, L.: Bpr: bayesian personalized ranking from implicit feedback. In: Conference on Uncertainty in Artificial Intelligence (2009)
Wang, H., Zhang, F., Min, H., Xing, X., Guo, M., Qi, L.: Shine: signed heterogeneous information network embedding for sentiment link prediction (2017)
Wang, H., Zhang, F., Xing, X., Guo, M.: Dkn: Deep knowledge-aware network for news recommendation (2018)
Wang, X., et al.: Dynamic attention deep model for article recommendation by learning human editors’ demonstration. In: ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (2017)
Xiao, Y., Xiang, R., Sun, Y., Gu, Q., Han, J.: Personalized entity recommendation: a heterogeneous information network approach (2014)
Yu, J., Min, G., Li, J., Yin, H., Liu, H.: Adaptive implicit friends identification over heterogeneous network for social recommendation. pp. 357–366 (2018)
Zhang, F., Yuan, N.J., Lian, D., Xie, X., Ma, W.Y.: Collaborative knowledge base embedding for recommender systems. In: ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (2016)
Zhen, W., Zhang, J., Feng, J., Zheng, C.: Knowledge graph embedding by translating on hyperplanes. In: Twenty-Eighth AAAI Conference on Artificial Intelligence (2014)
Acknowledgements
This research is supported by graduate research and innovation foundation of Chongqing,China(Grant No. CVS19052), the Fundamental Research Funds for the Central Universities (No. 2019CDXYRJ0011), the National Key Research and Development Program of China (No. 2018YFF0214706), Chongqing Research Program of Basic Research and Frontier Technology (No. cstc2017jcyjBX0025) and Science and Technology Major Special Project of Guangxi (GKAA17129002).
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
Wang, X., Gao, M., Lu, Z., Wang, Z., Zhang, J., Zhang, Y. (2019). DMCM: A Deep Multi-Channel Model for Dynamic Movie Recommendation. In: Gedeon, T., Wong, K., Lee, M. (eds) Neural Information Processing. ICONIP 2019. Communications in Computer and Information Science, vol 1142. Springer, Cham. https://doi.org/10.1007/978-3-030-36808-1_46
Download citation
DOI: https://doi.org/10.1007/978-3-030-36808-1_46
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-36807-4
Online ISBN: 978-3-030-36808-1
eBook Packages: Computer ScienceComputer Science (R0)