Abstract
Multi-behavior recommendation models exploit diverse behaviors of users (e.g., page view, add-to-cart, and purchase) and successfully alleviate the data sparsity and cold-start problems faced by classical recommendation methods. In real-world scenarios, the interactive behaviors between users and items are often complex and highly dependent. Existing multi-behavior recommendation models do not fully utilize multi-behavior information in the following two aspects: (1) The diversity of user behavior resulting from the individualization of users’ intents. (2) The loss of user multi-behavior information due to inappropriate information fusion. To fill this gap, we hereby propose a multi-behavior graph contrast network (MORO). Firstly, MORO constructs multiple behavior representations of users from different behavior graphs and aggregate these representations based on behavior intents of each user. Secondly, MORO develops a contrast enhancement module to capture information of high-order heterogeneous paths and reduce information loss. Extensive experiments on three real-world datasets show that MORO outperforms state-of-the-art baselines. Furthermore, the preference analysis implies that MORO can accurately model user multi-behavior preferences.
This work was supported by the National Natural Science Foundation of China (61972268), the National Key Research and Development Program of China (2018YFB0704301-1), Med-X Center for Informatics Funding Project (YGJC001).
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
Chen, C., et al.: Graph heterogeneous multi-relational recommendation. In: AAAI, pp. 3958–3966 (2021)
Du, C., Li, C., Zheng, Y., Zhu, J., Zhang, B.: Collaborative filtering with user-item co-autoregressive models. In: AAAI, pp. 2175–2182 (2018)
Gao, C., et al.: Neural multi-task recommendation from multi-behavior data. In: ICDE, pp. 1554–1557 (2019)
Guo, L., Hua, L., Jia, R., Zhao, B., Wang, X., Cui, B.: Buying or browsing?: predicting real-time purchasing intent using attention-based deep network with multiple behavior. In: KDD, pp. 1984–1992 (2019)
He, X., Liao, L., Zhang, H., Nie, L., Hu, X., Chua, T.: Neural collaborative filtering. In: WWW, pp. 173–182 (2017)
Jin, B., Gao, C., He, X., Jin, D., Li, Y.: Multi-behavior recommendation with graph convolutional networks. In: SIGIR, pp. 659–668 (2020)
Koren, Y., Bell, R.M., Volinsky, C.: Matrix factorization techniques for recommender systems. Computer 42(8), 30–37 (2009)
Mao, K., Zhu, J., Xiao, X., Lu, B., Wang, Z., He, X.: Ultragcn: ultra simplification of graph convolutional networks for recommendation. In: CIKM, pp. 1253–1262 (2021)
van den Oord, A., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. CoRR abs/1807.03748 (2018)
Rendle, S., Freudenthaler, C., Gantner, Z., Schmidt-Thieme, L.: BPR: Bayesian personalized ranking from implicit feedback. In: UAI, pp. 452–461 (2009)
Schlichtkrull, M.S., Kipf, T.N., Bloem, P., van den Berg, R., Titov, I., Welling, M.: Modeling relational data with graph convolutional networks. In: ESWC, vol. 10843, pp. 593–607 (2018)
Sedhain, S., Menon, A.K., Sanner, S., Xie, L.: AutoRec: autoencoders meet collaborative filtering. In: WWW, pp. 111–112 (2015)
Wang, X., He, X., Wang, M., Feng, F., Chua, T.: Neural graph collaborative filtering. In: SIGIR, pp. 165–174 (2019)
Wu, S., Zhang, Y., Gao, C., Bian, K., Cui, B.: GARG: anonymous recommendation of point-of-interest in mobile networks by graph convolution network. Data Sci. Eng. 5(4), 433–447 (2020)
Wu, Y., DuBois, C., Zheng, A.X., Ester, M.: Collaborative denoising auto-encoders for top-n recommender systems. In: WSDM, pp. 153–162 (2016)
Xia, L., Huang, C., Xu, Y., Dai, P.: Multi-behavior enhanced recommendation with cross-interaction collaborative relation modeling. In: ICDE, pp. 659–668 (2021)
Xia, L., Huang, C., Xu, Y., Dai, P., Zhang, B., Bo, L.: Multiplex behavioral relation learning for recommendation via memory augmented transformer network. In: SIGIR, pp. 2397–2406 (2020)
Xia, L., et al.: Knowledge-enhanced hierarchical graph transformer network for multi-behavior recommendation. In: AAAI, pp. 4486–4493 (2021)
Xia, L., Xu, Y., Huang, C., Dai, P., Bo, L.: Graph meta network for multi-behavior recommendation. In: SIGIR, pp. 757–766 (2021)
Xue, H., Dai, X., Zhang, J., Huang, S., Chen, J.: Deep matrix factorization models for recommender systems. In: IJCAI, pp. 3203–3209 (2017)
Yu, S., et al.: Leveraging tripartite interaction information from live stream e-commerce for improving product recommendation. In: KDD, pp. 3886–3894 (2021)
Zang, Y., Liu, Y.: GISDCN: a graph-based interpolation sequential recommender with deformable convolutional network. In: DASFAA, vol. 13246, pp. 289–297 (2022)
Zhang, W., Mao, J., Cao, Y., Xu, C.: Multiplex graph neural networks for multi-behavior recommendation. In: CIKM, pp. 2313–2316 (2020)
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 Switzerland AG
About this paper
Cite this paper
Jiang, W., Duan, L., Ding, X., Chen, X. (2023). MORO: A Multi-behavior Graph Contrast Network for Recommendation. In: Li, B., Yue, L., Tao, C., Han, X., Calvanese, D., Amagasa, T. (eds) Web and Big Data. APWeb-WAIM 2022. Lecture Notes in Computer Science, vol 13423. Springer, Cham. https://doi.org/10.1007/978-3-031-25201-3_9
Download citation
DOI: https://doi.org/10.1007/978-3-031-25201-3_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-25200-6
Online ISBN: 978-3-031-25201-3
eBook Packages: Computer ScienceComputer Science (R0)