Abstract
Cross-Domain Recommendation (CDR) has been proved helpful in dealing with two bottlenecks in recommendation scenarios: data sparsity and cold start. Recent research reveals that identifying domain-invariant and domain-specific features behind interactions aids in generating comprehensive user and item representations. However, we argue that existing methods fail to separate domain-invariant and domain-specific representations from each other, which may contain noise and redundancy when treating domain-invariant representations as shared information across domains and harm recommendation performance. In this paper, we propose a novel Disentangled Contrastive Learning for Cross-Domain Recommendation framework (DCCDR) to disentangle domain-invariant and domain-specific representations to make them more informative. Specifically, we propose a separate representation generation component to generate separate domain-invariant and domain-specific representations for each domain. Next, We enrich the representations through multi-order collaborative information with GNNs. Moreover, we design a mutual-information-based contrastive learning objective to produce additional supervision signals for disentanglement and enhance the informativeness of disentangled representations by reducing noise and redundancy. Extensive experiments on two real-world datasets show that our proposed DCCDR model outperforms state-of-the-art single-domain and cross-domain recommendation approaches.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Bengio, Y., Courville, A., Vincent, P.: Representation learning: a review and new perspectives. IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1798–1828 (2013)
Cao, J., Lin, X., Cong, X., Ya, J., Liu, T., Wang, B.: DisenCDR: learning disentangled representations for cross-domain recommendation. In: SIGIR, pp. 267–277 (2022)
Chen, C., et al.: An efficient adaptive transfer neural network for social-aware recommendation. In: SIGIR, pp. 225–234 (2019)
Cui, Q., Wei, T., Zhang, Y., Zhang, Q.: HeroGRAPH: a heterogeneous graph framework for multi-target cross-domain recommendation. In: ORSUM@ RecSys (2020)
Duan, L., Tsang, I.W., Xu, D., Chua, T.S.: Domain adaptation from multiple sources via auxiliary classifiers. In: ICML, pp. 289–296 (2009)
Hamilton, W., Ying, Z., Leskovec, J.: Inductive representation learning on large graphs. In: Advances in Neural Information Processing Systems, vol. 30 (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)
He, X., Liao, L., Zhang, H., Nie, L., Hu, X., Chua, T.: Neural collaborative filtering. In: WWW, pp. 173–182 (2017)
Hu, G., Zhang, Y., Yang, Q.: CoNet: collaborative cross networks for cross-domain recommendation. In: CIKM, pp. 667–676 (2018)
Huang, L., Zhao, Z.L., Wang, C.D., Huang, D., Chao, H.Y.: LSCD: low-rank and sparse cross-domain recommendation. Neurocomputing 366, 86–96 (2019)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)
Li, J., Peng, Z., Wang, S., Xu, X., Yu, P.S., Hao, Z.: Heterogeneous graph embedding for cross-domain recommendation through adversarial learning. In: Nah, Y., Cui, B., Lee, S.-W., Yu, J.X., Moon, Y.-S., Whang, S.E. (eds.) DASFAA 2020. LNCS, vol. 12114, pp. 507–522. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-59419-0_31
Li, N., Gao, C., Jin, D., Liao, Q.: Disentangled modeling of social homophily and influence for social recommendation. In: TKDE (2022)
Li, P., Tuzhilin, A.: DDTCDR: deep dual transfer cross domain recommendation. In: WSDM, pp. 331–339 (2020)
Liu, J., et al.: Exploiting aesthetic preference in deep cross networks for cross-domain recommendation. In: Proceedings of The Web Conference 2020, pp. 2768–2774 (2020)
Liu, M., Li, J., Li, G., Pan, P.: Cross domain recommendation via bi-directional transfer graph collaborative filtering networks. In: CIKM, pp. 885–894 (2020)
Ma, H., Yang, H., Lyu, M.R., King, I.: SoRec: social recommendation using probabilistic matrix factorization. In: CIKM, pp. 931–940 (2008)
Ma, J., Zhou, C., Cui, P., Yang, H., Zhu, W.: Learning disentangled representations for recommendation. In: NeuIPS, vol. 32 (2019)
Ma, J., Zhou, C., Yang, H., Cui, P., Wang, X., Zhu, W.: Disentangled self-supervision in sequential recommenders. In: KDD, pp. 483–491 (2020)
Man, T., Shen, H., Jin, X., Cheng, X.: Cross-domain recommendation: an embedding and mapping approach. In: IJCAI, vol. 17, pp. 2464–2470 (2017)
Oord, A.V.D., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)
Qiu, R., Huang, Z., Yin, H.: Memory augmented multi-instance contrastive predictive coding for sequential recommendation. In: ICDM, pp. 519–528 (2021)
Singh, A.P., Gordon, G.J.: Relational learning via collective matrix factorization. In: KDD, pp. 650–658 (2008)
Velickovic, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., Bengio, Y.: Graph attention networks. Stat 1050, 20 (2017)
Wang, K., Zhu, Y., Liu, H., Zang, T., Wang, C., Liu, K.: Inter-and intra-domain relation-aware heterogeneous graph convolutional networks for cross-domain recommendation. In: DASFAA, pp. 53–68 (2022)
Wang, X., Jin, H., Zhang, A., He, X., Xu, T., Chua, T.S.: Disentangled graph collaborative filtering. In: SIGIR, pp. 1001–1010 (2020)
Wang, Y., Tang, S., Lei, Y., Song, W., Wang, S., Zhang, M.: DisenHAN: disentangled heterogeneous graph attention network for recommendation. In: CIKM, pp. 1605–1614 (2020)
Wu, J., et al.: Self-supervised graph learning for recommendation. In: SIGIR, pp. 726–735 (2021)
Wu, J., et al.: DisenKGAT: knowledge graph embedding with disentangled graph attention network. In: CIKM, pp. 2140–2149 (2021)
Xia, X., Yin, H., Yu, J., Wang, Q., Cui, L., Zhang, X.: Self-supervised hypergraph convolutional networks for session-based recommendation. In: AAAI, vol. 35, pp. 4503–4511 (2021)
Xin, X., Liu, Z., Lin, C.Y., Huang, H., Wei, X., Guo, P.: Cross-domain collaborative filtering with review text. In: IJCAI (2015)
Xu, K., Xie, Y., Chen, L., Zheng, Z.: Expanding relationship for cross domain recommendation. In: CIKM, pp. 2251–2260 (2021)
Yan, H., Chen, X., Gao, C., Li, Y., Jin, D.: DeepAPF: deep attentive probabilistic factorization for multi-site video recommendation. TC 2(130), 17–883 (2019)
Yu, W., Lin, X., Ge, J., Ou, W., Qin, Z.: Semi-supervised collaborative filtering by text-enhanced domain adaptation. In: KDD, pp. 2136–2144 (2020)
Zang, T., Zhu, Y., Liu, H., Zhang, R., Yu, J.: A survey on cross-domain recommendation: taxonomies, methods, and future directions. ACM Trans. Inf. Syst. 41(2), 1–39 (2022)
Zang, T., Zhu, Y., Zhu, J., Xu, Y., Liu, H.: MPAN: multi-parallel attention network for session-based recommendation. Neurocomputing 471, 230–241 (2022)
Zhao, C., Li, C., Fu, C.: Cross-domain recommendation via preference propagation GraphNet. In: CIKM, pp. 2165–2168 (2019)
Zhao, X., Yang, N., Yu, P.S.: Multi-sparse-domain collaborative recommendation via enhanced comprehensive aspect preference learning. In: WSDM, pp. 1452–1460 (2022)
Zheng, Y., et al.: Disentangling long and short-term interests for recommendation. In: Proceedings of the ACM Web Conference 2022, pp. 2256–2267 (2022)
Zhu, F., Chen, C., Wang, Y., Liu, G., Zheng, X.: DTCDR: a framework for dual-target cross-domain recommendation. In: CIKM, pp. 1533–1542 (2019)
Zhu, F., Wang, Y., Chen, C., Liu, G., Zheng, X.: A graphical and attentional framework for dual-target cross-domain recommendation. In: IJCAI, pp. 3001–3008 (2020)
Zhu, F., Wang, Y., Chen, C., Zhou, J., Li, L., Liu, G.: Cross-domain recommendation: challenges, progress, and prospects. arXiv preprint arXiv:2103.01696 (2021)
Acknowledgement
This research is supported in part by National Science Foundation of China (No. 62072304, No. 61772341, No. 61832013, No. 62172277, No. 62272320), Shanghai Municipal Science and Technology Commission (No. 19510760500, No. 21511104700, No. 19511120300), and Zhejiang Aoxin Co. Ltd.
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
Zhang, R., Zang, T., Zhu, Y., Wang, C., Wang, K., Yu, J. (2023). Disentangled Contrastive Learning for Cross-Domain Recommendation. In: Wang, X., et al. Database Systems for Advanced Applications. DASFAA 2023. Lecture Notes in Computer Science, vol 13944. Springer, Cham. https://doi.org/10.1007/978-3-031-30672-3_11
Download citation
DOI: https://doi.org/10.1007/978-3-031-30672-3_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-30671-6
Online ISBN: 978-3-031-30672-3
eBook Packages: Computer ScienceComputer Science (R0)