Abstract
Traditionally, the search and recommendation tasks are performed separately, by distinct models. Having a unique model for the two tasks is however particularly appealing for platforms that offer search and recommendation services to a shared user base over common items. In this paper, we study this unification scenario denoted as Joint Personalized Search and Recommendation (JPSR). To tackle this problem, we introduce HyperSaR, an hypergraph convolutional approach for search and recommendation. From the interaction data, we first build an hypergraph composed of user, item and query keyword nodes in which recommendation instances form user-item edges and search instances define user-item-query hyperedges. We then propagate user, item and query keyword embeddings using hypergraph convolution, and train HyperSaR with the combination of two complementary losses. The first one amounts to assessing the probability of an interaction, while the second one aims at predicting the query of a search interaction given a (user, item) pair. The proposed method is evaluated on the JPSR task using three datasets: a real-world, industrial dataset, and the public MovieLens and Lastfm datasets, which have been adapted to the task. Our experiments demonstrate the superior effectiveness of HyperSaR over competing approaches.
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
Notes
- 1.
- 2.
- 3.
Some previous works [1,2,3, 11, 27, 28] used Amazon datasets for product search. However the common practice [19] is to define synthetic queries from product categories, which do not result from a user-specific expression. Therefore, we advocate that such datasets are not suitable for personalized search and, a fortiori, for JPSR.
- 4.
- 5.
- 6.
- 7.
For these approaches, the search instances are simply considered as user-item pairs by ignoring queries. The same interaction set is then used as for other methods.
- 8.
Originally, JSR is based on text descriptions attached to items; we adapt the approach to the JPSR task by using the queries in replacement of item descriptions and by linking each query to its interaction instead of its item.
- 9.
- 10.
In our setting, items are not associated with text documents, preventing the usage of standard retrieval methods. To apply BM25, we form documents by concatenating training queries pertaining to the same item, and use them for retrieval on test queries.
- 11.
References
Ai, Q., Vishwanathan, S.V., Hill, D.N., Bruce Croft, W.: A zero attention model for personalized product search. In: CIKM, pp. 379–388 (2019)
Ai, Q., Zhang, Y., Bi, K., Bruce Croft, W.: Explainable product search with a dynamic relation embedding model. ACM Trans. Inf. Syst. 38(1) (2020)
Ai, Q., Zhang, Y., Bi, K., Chen, X., Bruce Croft, W.: Learning a hierarchical embedding model for personalized product search. In: SIGIR, pp. 645–654 (2017)
Bai, S., Zhang, F., Torr, P.H.: Hypergraph convolution and hypergraph attention. Pattern Recognit. 110, 1–30 (2021)
Chen, L., Wu, L., Hong, R., Zhang, K., Wang, M.: Revisiting graph based collaborative filtering: a linear residual graph convolutional network approach. In: AAAI, pp. 27–34 (2020)
Dong, Y., Sawin, W., Bengio, Y.: HNHN: hypergraph networks with hyperedge neurons. arXiv:2006.12278 (2020)
Feng, Y., You, H., Zhang, Z., Ji, R., Gao, Y.: Hypergraph neural networks. In: AAAI, pp. 3558–3565 (2019)
Guo, H., Tang, R., Ye, Y., Li, Z., He, X.: DeepFM: a factorization-machine based neural network for CTR prediction. In: IJCAI, pp. 1725–1731 (2017)
He, X., Deng, K., Wang, X., Li, Y., Zhang, Y., Wang, M.: LightGCN: simplifying and powering graph convolution network for recommendation. In: SIGIR, pp. 639–648 (2020)
Koren, Y., Bell, R.M., Volinsky, C.: Matrix factorization techniques for recommender systems. Computer 42(8), 30–37 (2009)
Liu, S., Gu, W., Cong, G., Zhang, F.: Structural relationship representation learning with graph embedding for personalized product search. In: CIKM, pp. 915–924 (2020)
Park, E.L., Cho, S.: KoNLPy: Korean natural language processing in Python. In: HCLT (2014)
Rendle, S.: Factorization machines. In: ICDM, pp. 995–1000 (2010)
Rendle, S., Freudenthaler, C., Gantner, Z., Schmidt-Thieme, L.: BPR: Bayesian personalized ranking from implicit feedback. In: UAI, pp. 452–461 (2009)
Rendle, S., Krichene, W., Zhang, L., Anderson, J.: Neural collaborative filtering vs. matrix factorization revisited. arXiv:2005.09683 (2020)
Rong, Y., Huang, W., Xu, T., Huang, J.: DropEdge: towards deep graph convolutional networks on node classification. In: ICLR (2020)
Sparck Jones, K., Walker, S., Robertson, S.E.: A probabilistic model of information retrieval: development and comparative experiments - Part 2. Inf. Process. Manage. 36(6), 809–840 (2000)
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)
Van Gysel, C., de Rijke, M., Kanoulas, E.: Learning latent vector spaces for product search. In: CIKM, pp. 165–174 (2016)
Wang, J., Ding, K., Hong, L., Liu, H., Caverlee, J.: Next-item recommendation with sequential hypergraphs. In: SIGIR, pp. 1101–1110 (2020)
Wang, J., Ding, K., Zhu, Z., Caverlee, J.: Session-based recommendation with hypergraph attention networks. In: SDM, pp. 82–90 (2021)
Wang, X., He, X., Wang, M., Feng, F., Chua, T.S.: Neural graph collaborative filtering. In: SIGIR, pp. 165–174 (2019)
Wu, F., Zhang, T., de Souza, A.H., Fifty, C., Yu, T., Weinberger, K.Q.: Simplifying graph convolutional networks. In: ICML, pp. 11884–11894 (2019)
Wu, S., Zhang, W., Sun, F., Cui, B.: Graph neural networks in recommender systems: a survey. arXiv:2011.02260 (2020)
Wu, T., et al.: Zero-shot heterogeneous transfer learning from recommender systems to cold-start search retrieval. In: CIKM, pp. 2821–2828 (2020)
Ying, R., He, R., Chen, K., Eksombatchai, P., Hamilton, W.L., Leskovec, J.: Graph convolutional neural networks for web-scale recommender systems. In: KDD, pp. 974–983 (2018)
Zamani, H., Croft, W.B.: Joint modeling and optimization of search and recommendation. In: DESIRES, pp. 36–41 (2018)
Zamani, H., Croft, W.B.: Learning a joint search and recommendation model from user-item interactions. In: WSDM, pp. 717–725 (2020)
Zhang, R., Guo, J., Fan, Y., Lan, Y., Cheng, X.: Query understanding via intent description generation. In: CIKM, pp. 1823–1832 (2020)
Zhang, Y., Chen, X., Ai, Q., Yang, L., Croft, W.B.: Towards conversational search and recommendation: system ask, user respond. In: CIKM, pp. 177–186 (2018)
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
Thonet, T., Renders, JM., Choi, M., Kim, J. (2022). Joint Personalized Search and Recommendation with Hypergraph Convolutional Networks. In: Hagen, M., et al. Advances in Information Retrieval. ECIR 2022. Lecture Notes in Computer Science, vol 13185. Springer, Cham. https://doi.org/10.1007/978-3-030-99736-6_30
Download citation
DOI: https://doi.org/10.1007/978-3-030-99736-6_30
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-99735-9
Online ISBN: 978-3-030-99736-6
eBook Packages: Computer ScienceComputer Science (R0)