Abstract
Many e-commerce platforms such as JD.com and Taobao have implemented personalized recommendation systems. Query recommendation or relevant search module is introduced to guide users to clarify their shopping intentions. In this paper, we present a novel Session based Query Recommendation with Graph neural networks on Heterogeneous information trees (SQRGH). We model user click behaviors (user-query-item) as a heterogeneous information tree to better present user behaviors (Fig. 2). We use graph neural networks to model interactions in user behavior, while, instead of using real queries or items as nodes, we use the click behaviors as virtual nodes to better learn about changes in the user intention, and use the identity matrix to upgrade adjacency matrices generated by traditional methods. On a real large-scale dataset in e-commerce using the JD computing platform, our proposed SQRGH method has superior performance and can recommend more reliable and reasonable results.
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
Cao, H., et al.: Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 875–883. ACM (2008)
Zhang, Z., Nasraoui, O.: Proceedings of the 15th International Conference on World Wide Web, pp. 1039–1040. ACM (2006)
Sheil, H.: Discovering user intent in e-commerce clickstreams. Ph.D. thesis, Cardiff University (2019)
Hidasi, B., Karatzoglou, A., Baltrunas, L., Tikk, D.: arXiv preprint arXiv:1511.06939 (2015)
Xu, C., et al.: Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI), pp. 3940–3946 (2019)
Jiang, J.Y., Wang, W.: Proceedings of the 27th ACM International Conference on Information and Knowledge Management, pp. 197–206. ACM (2018)
Han, X., Shi, C., Wang, S., Philip, S.Y., Song, L.: IJCAI 3393–3399 (2018)
Zhang, C., Song, D., Huang, C., Swami, A., Chawla, N.V.: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 793–803 (2019)
He, Y., Song, Y., Li, J., Ji, C., Peng, J., Peng, H.: Proceedings of the 28th ACM International Conference on Information and Knowledge Management, pp. 639–648 (2019)
Fan, S., et al.: Metapath-guided heterogeneous graph neural network for intent recommendation. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, (2019)
Wu, S., Tang, Y., Zhu, Y., Wang, L., Xie, X., Tan, T.: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 346–353 (2019)
Bonchi, F., Perego, R., Silvestri, F., Vahabi, H., Venturini, R.: Proceedings of the 20th International Conference Companion on World Wide Web, pp. 15–16. ACM (2011)
Mikolov, T., Chen, K., Corrado, G., Dean, J.: arXiv preprint arXiv:1301.3781 (2013)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Zheng, J., Yu, K., Ge, Z., Wu, X., Xu, S., Yan, W. (2021). Session Based Query Recommendation with Graph Neural Networks on Heterogeneous Information Trees. In: Meng, H., Lei, T., Li, M., Li, K., Xiong, N., Wang, L. (eds) Advances in Natural Computation, Fuzzy Systems and Knowledge Discovery. ICNC-FSKD 2020. Lecture Notes on Data Engineering and Communications Technologies, vol 88. Springer, Cham. https://doi.org/10.1007/978-3-030-70665-4_177
Download citation
DOI: https://doi.org/10.1007/978-3-030-70665-4_177
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-70664-7
Online ISBN: 978-3-030-70665-4
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)