Abstract
Session-based recommender systems (SBRSs) aim at predicting the next item by modelling the complex dependencies within and across sessions. Most of the existing SBRSs make recommendations only based on local dependencies (i.e., the dependencies between items within a session), while ignoring global dependencies (i.e., the dependencies across multiple sessions), leading to information loss and thus reducing the recommendation accuracy. Moreover, they are usually not able to recommend cold-start items effectively due to their limited session information. To alleviate these shortcomings of SBRSs, we propose a novel heterogeneous mixed graph learning (HMGL) framework to effectively learn both local and global dependencies for next-item recommendations. The HMGL framework mainly contains a heterogeneous mixed graph (HMG) construction module and an HMG learning module. The HMG construction module map both the session information and the item attribute information into a unified graph to connect items within and across sessions. The HMG learning module learns a unified representation for each item by simultaneously modelling the local and global dependencies over the HMG. The learned representation is then used for next-item recommendations. Results of extensive experiments on real-world datasets show the superiority of HMGL framework over the start-of-the-art methods in terms of recommendation accuracy.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Hidasi, B., Karat-zoglou, A., et al.: Session based recommendations with recurrent neural networks. In: ICLR, pp. 1–10 (2016)
Hidasi, B., Karat-zoglou, A., et al.: Recurrent neural networks with top-k gains for session-based recommendations. In: CIKM, pp. 843–852 (2018)
Xu, C., Zhao, P., et al.: Graph contextualized self attention network for session-based recommendation. In: IJCAI, pp. 3940–3946 (2019)
Yuan, F., Karatzoglou, A., et al.: A simple convolutional generative network for next item recommendation. In: WSDM, pp. 582–590 (2019)
Yu, F., Zhu, Y., et al.: TAGNN: target attentive graph neural networks for session-based recommendation. In: SIGIR, pp. 1–5 (2020)
Ying, H., Zhuang, F., et al.: Sequential recommender system based on hierarchical attention networks. In: IJCAI, pp. 3926–3932 (2018)
Linden, G., Smith, B., York, J.: Amazon.com recommendations: item-to-item collaborative filtering. IEEE Internet Comput. 7(1), 76–80 (2003)
Li, Y., Tarlow, D., et al.: Gated graph sequence neural networks. In: ICLR, pp. 1–14 (2015)
Liu, Q., Zeng, Y., et al.: STAMP: short-term attention/memory priority model for session-based recommendation. In: KDD, pp. 1831–1839 (2018)
Ruocco, M., Skrede, O.S.L., et al.: Inter-session modeling for session-based recommendation. In: 2nd Workshop on DLRS, pp. 24–31 (2017)
Rendle, S., Freudenthaler, C., et al.: Factorizing personalized Markov chains for next-basket recommendation. In: WWW, pp. 811–820 (2010)
Forsati, R., Meybodi, M.R., et al.: Web page personalization based on weighted association rules. In: ICECT, pp. 130–135 (2009)
Qiu, R., Li, J., et al.: Rethinking the item order in session-based recommendation with graph neural networks. In: CIKM, pp. 579–588 (2019)
Feng, S., Li, X., et al.: Personalized ranking metric embedding for next new POI recommendation. In: IJCAI, pp. 2069–2075 (2015)
Wu, S., Tang, Y., et al.: Session-based recommendation with graph neural networks. In: AAAI, pp. 346–353 (2018)
Wang, S., Hu, L., et al.: Modeling multi-purpose sessions for next-item recommendations via mixture-channel purpose routing networks. In: IJCAI, pp. 3771–3777 (2019)
Wang, S., Cao, L.: Inferring implicit rules by learning explicit and hidden item dependency. IEEE Trans. Syst. Man Cybern. Syst. 50(3), 935–946 (2020)
Wang, S., Hu, L., et al.: Intention nets: psychology-inspired user choice behavior modeling for next-basket prediction. In: AAAI, pp. 6259–6266 (2020)
Wang, S., Hu, L., et al.: Attention-based transactional context embedding for next-item recommendation. In: AAAI, pp. 2532–2539 (2018)
Wang, W., Zhang, W., et al.: Beyond clicks: modeling multi-relational item graph for session-based target behavior prediction. In: WWW, pp. 3926–3932 (2020)
Li, X., Yin, H., et al.: Semi-supervised Clustering with Deep Metric Learning and Graph Embedding. World Wide Web 23(2), 781–798 (2020). https://doi.org/10.1007/s11280-019-00723-8
Wang, Y., Feng, C., Chen, L., Yin, H., Guo, C., Chu, Y.: User identity linkage across social networks via linked heterogeneous network embedding. World Wide Web 22(6), 2611–2632 (2018). https://doi.org/10.1007/s11280-018-0572-3
Wang, Z., Liu, H., et al.: Unified embedding model over heterogeneous information network for personalized recommendation. In: IJCAI, pp. 3813–3819 (2019)
Acknowledgements
This work was supported by ARC Discovery Project DP180102378.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Wang, N., Wang, S., Wang, Y., Sheng, Q.Z., Orgun, M. (2020). Modelling Local and Global Dependencies for Next-Item Recommendations. In: Huang, Z., Beek, W., Wang, H., Zhou, R., Zhang, Y. (eds) Web Information Systems Engineering – WISE 2020. WISE 2020. Lecture Notes in Computer Science(), vol 12343. Springer, Cham. https://doi.org/10.1007/978-3-030-62008-0_20
Download citation
DOI: https://doi.org/10.1007/978-3-030-62008-0_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-62007-3
Online ISBN: 978-3-030-62008-0
eBook Packages: Computer ScienceComputer Science (R0)