Abstract
Graph neural networks (GNNs) have gained impressive success in the task of sequential recommendation due to their advantage in obtaining the complex transition patterns of items. However, existing GNN-based sequential recommenders still face some problems: (1) The global order information is lost when converting a sequence into a graph. (2) The long-term dependencies in a sequence are ignored due to the over-smoothing problem in GNNs. In this paper, we propose an order-aware GNN with long-range connections (OAG-LC) for sequence modeling. To capture the global order of a sequence, a novel graph update mechanism is proposed, which evolves the graph embedding recurrently over time rather than concurrently for order preservation. And a novel gate is used to incorporate both order and structural information in the update phase. To model the long-term dependencies of user behaviors, we convert the sequence into a graph via reachability and apply the attention mechanism for information propagation through the long-range connections. Furthermore, the proposed graph construction method differentiated repeated items with their positions for information lossless encoding. We conduct extensive experiments on four public datasets, and the experimental results demonstrate the effectiveness of our proposed model.
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
Beutel, A., Covington, P., et al.: Latent cross: making use of context in recurrent recommender systems. In: Proceedings of the 11th WSDM, pp. 46–54 (2018)
Chen, T., Wong, R.C.W.: Handling information loss of graph neural networks for session-based recommendation. In: Proceedings of the 26th ACM SIGKDD, pp. 1172–1180 (2020)
Hidasi, B., Karatzoglou, A., et al.: Session-based recommendations with recurrent neural networks. In: Proceedings of the 3rd ICLR (2016)
Kang, W.C., McAuley, J.: Self-attentive sequential recommendation. In: Proceedings of the 18th ICDM, pp. 197–206. IEEE (2018)
Li, J., Ren, P., Chen, Z., et al.: Neural attentive session-based recommendation. In: Proceedings of the 27th CIKM, pp. 1419–1428 (2017)
Li, Q., Han, Z., Wu, X.M.: Deeper insights into graph convolutional networks for semi-supervised learning. In: Proceedings of the 32nd AAAI, vol. 32 (2018)
Liu, Q., Zeng, Y., et al.: STAMP: short-term attention/memory priority model for session-based recommendation. In: Proceedings of the 24th SIGKDD, pp. 1831–1839 (2018)
Ludewig, M., Jannach, D.: Evaluation of session-based recommendation algorithms. User Model. User-Adap. Inter. 28(4–5), 331–390 (2018)
Pan, Z., Cai, F., Chen, W., et al.: Star graph neural networks for session-based recommendation. In: Proceedings of the 29th CIKM, pp. 1195–1204 (2020)
Qiu, R., Li, J., Huang, Z., et al.: Rethinking the item order in session-based recommendation with graph neural networks. In: Proceedings of the 28th CIKM, pp. 579–588 (2019)
Shani, G., Heckerman, D., Brafman, R.I.: An MDP-based recommender system. J. Mach. Learn. Res. 6(Sep), 1265–1295 (2005)
Song, Q., et al.: Incremental matrix factorization via feature space re-learning for recommender system. In: Proceedings of the 9th Recsys, pp. 277–280 (2015)
Sun, K., Qian, T., Yin, H., Chen, T., Chen, Y., Chen, L.: What can history tell us? In: Proceedings of the 28th CIKM, pp. 1593–1602 (2019)
Wu, S., Tang, Y., et al.: Session-based recommendation with graph neural networks. In: Proceedings of the 33rd AAAI, vol. 33, pp. 346–353 (2019)
Xu, C., Zhao, P., Liu, Y., et al.: Graph contextualized self-attention network for session-based recommendation. In: Proceedings of the 28th IJCAI, vol. 19, pp. 3940–3946 (2019)
Yu, Z., Lian, J., Mahmoody, A., et al.: Adaptive user modeling with long and short-term preferences for personalized recommendation. In: Proceedings of the 28th IJCAI, pp. 4213–4219 (2019)
Zhao, W.X., Mu, S., Hou, Y., et al.: RecBole: towards a unified, comprehensive and efficient framework for recommendation algorithms. arXiv preprint arXiv:2011.01731 (2020)
Acknowledgements
This work was supported by NSFC grants (No. 62136002 and 61972155), the Science and Technology Commission of Shanghai Municipality (20DZ1100300) and the Open Project Fund from Shenzhen Institute of Artificial Intelligence and Robotics for Society, under Grant No. AC01202005020, Shanghai Knowledge Service Platform Project (No. ZF1213), Shanghai Trusted Industry Internet Software Collaborative Innovation Center.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Zhang, X., Ji, W., Yuan, J., Wang, X. (2022). Order-Aware Graph Neural Network for Sequential Recommendation. In: Gama, J., Li, T., Yu, Y., Chen, E., Zheng, Y., Teng, F. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2022. Lecture Notes in Computer Science(), vol 13280. Springer, Cham. https://doi.org/10.1007/978-3-031-05933-9_23
Download citation
DOI: https://doi.org/10.1007/978-3-031-05933-9_23
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-05932-2
Online ISBN: 978-3-031-05933-9
eBook Packages: Computer ScienceComputer Science (R0)