Abstract
The session-based recommendation aims to generate personalized item suggestions by using short-term anonymous sessions to model user behavior and preferences. Early studies cast the session-based recommendation as a personalized ranking task, and adopt graph neural networks to aggregate information about users and items. Although these methods are effective to some extent, they have primarily focused on adjacent items tightly connected in the session graphs in general and overlooked the global preference representation. In addition, it is difficult to overcome the special properties of popularity bias in the real-world scenario. To address these issues, we propose a new method named GENE, short for Global Enhanced Graph Neural Network Embedding, to learn the session graph representations for the downstream session-based recommendation. Our model consists of three components. First, we propose to construct the session graph based on the order in which the items interact in the session with normalization. Second, we employ a graph neural network to obtain the latent vectors of items, then we represent the session graph by attention mechanisms. Third, we explore the session representation fusion for prediction incorporating linear transformation. The three components are integrated in a principled way for deriving a more accurate item list. Both quantitative results and qualitative analysis verify the effectiveness and rationality of our GENE method.
X. Sun and D. Meng—These authors contribute equally to this work.
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
Zou, F., Qian, Y., Zhang, Z., Zhu, X., Chang, D.: A data mining approach for analyzing dynamic user needs on UGC platform. In: IEEM 2021, pp. 1067–1071 (2021)
Feng, P., Qian, Y., Liu, X., Li, G., Zhao, J.: Robust graph collaborative filtering algorithm based on hierarchical attention. In: Xing, C., Fu, X., Zhang, Y., Zhang, G., Borjigin, C. (eds.) WISA 2021. LNCS, vol. 12999, pp. 625–632. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-87571-8_54
Zhang, W., Yan, J., Wang, Z., Wang, J.: Neuro-symbolic interpretable collaborative filtering for attribute-based recommendation. In: WWW 2022, pp. 3229–3238 (2022)
Wang, Y., Zhou, Y., Chen, T., Zhang, J., Yang, W., Huang, Z.: Sequence-aware API recommendation based on collaborative filtering. Int. J. Softw. Eng. Knowl. Eng. 32(8), 1203–1228 (2022)
Wang, S., Cao, L., Wang, Y., Sheng, Q.Z., Orgun, M.A., Lian, D.: A survey on session-based recommender systems. ACM Comput. Surv. 54(7), 154:1–154:38 (2022)
Li, A., Zhu, J., Li, Z., Cheng, H.: Transition information enhanced disentangled graph neural networks for session-based recommendation. Expert Syst. Appl. 210, 118336 (2022)
Zhang, S., Huang, T., Wang, D.: Sequence contained heterogeneous graph neural network. In: IJCNN 2021, pp. 1–8 (2021)
Liu, C., Li, Y., Lin, H., Zhang, C.: GNNRec: gated graph neural network for session-based social recommendation model. J. Intell. Inf. Syst. 60(1), 137–156 (2023)
Zhang, D., et al.: ApeGNN: node-wise adaptive aggregation in GNNs for recommendation. In: WWW, pp. 759–769 (2023)
Zhang, Y., Shi, Z., Zuo, W., Yue, L., Liang, S., Li, X.: Joint personalized Markov chains with social network embedding for cold-start recommendation. Neurocomputing 386, 208–220 (2020)
Rendle, S., Freudenthaler, C., Schmidt-Thieme, L.: Factorizing personalized Markov chains for next-basket recommendation. In: WWW 2010, pp. 811–820 (2010)
Hidasi, B., Karatzoglou, A., Baltrunas, L., Tikk, D.: Session-based recommendations with recurrent neural networks. In: ICLR 2016 (2016)
Zhu, J., Xu, Y., Zhu, Y.: Modeling long-term and short-term interests with parallel attentions for session-based recommendation. In: Nah, Y., Cui, B., Lee, S.-W., Yu, J.X., Moon, Y.-S., Whang, S.E. (eds.) DASFAA 2020. LNCS, vol. 12114, pp. 654–669. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-59419-0_40
Zheng, Y., Liu, S., Li, Z., Wu, S.: DGTN: dual-channel graph transition network for session-based recommendation. In: ICDM 2020, pp. 236–242 (2020)
Guo, J., et al.: Learning multi-granularity consecutive user intent unit for session-based recommendation. In: WSDM 2022, pp. 343–352 (2022)
Wang, Z., Wei, W., Cong, G., Li, X., Mao, X., Qiu, M.: Global context enhanced graph neural networks for session-based recommendation. In: SIGIR 2020, pp. 169–178 (2020)
Wu, S., Tang, Y., Zhu, Y., Wang, L., Xie, X., Tan, T.: Session-based recommendation with graph neural networks. In: AAAI 2019, pp. 346–353 (2019)
Xu, C., et al.: Graph contextualized self-attention network for session-based recommendation. In: IJCAI 2019, pp. 3940–3946 (2019)
Yu, F., Zhu, Y., Liu, Q., Wu, S., Wang, L., Tan, T.: TAGNN: target attentive graph neural networks for session-based recommendation. In: SIGIR 2020, pp. 1921–1924 (2020)
Gupta, P., Garg, D., Malhotra, P., Vig, L., Shroff, G.: NISER: normalized item and session representations with graph neural networks. CoRR abs/1909.04276 (2019)
Sarwar, B.M., Karypis, G., Konstan, J.A., Riedl, J.: Item-based collaborative filtering recommendation algorithms. In: WWW 2001, pp. 285–295 (2001)
Li, J., Ren, P., Chen, Z., Ren, Z., Lian, T., Ma, J.: Neural attentive session-based recommendation. In: CIKM 2017, pp. 1419–1428 (2017)
Acknowledgment
This work was supported in part by the National Natural Science Foundation of China Youth Fund (No. 61902001) and the Undergraduate Teaching Quality Improvement Project of Anhui Polytechnic University (No. 2022lzyybj02). We would also thank the anonymous reviewers for their detailed comments, which have helped us to improve the quality of this work. All opinions, findings, conclusions, and recommendations in this paper are those of the authors and do not necessarily reflect the views of the funding agencies.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Sun, X., Meng, D., Gao, X., Zhang, L., Kong, C. (2023). GENE: Global Enhanced Graph Neural Network Embedding for Session-Based Recommendation. In: Yuan, L., Yang, S., Li, R., Kanoulas, E., Zhao, X. (eds) Web Information Systems and Applications. WISA 2023. Lecture Notes in Computer Science, vol 14094. Springer, Singapore. https://doi.org/10.1007/978-981-99-6222-8_15
Download citation
DOI: https://doi.org/10.1007/978-981-99-6222-8_15
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-6221-1
Online ISBN: 978-981-99-6222-8
eBook Packages: Computer ScienceComputer Science (R0)
