Abstract
Cross-Domain Recommendation can significantly mitigate the challenges posed by sparse data for recommendation systems. Relevant studies indicate domain-specific preferences negatively impact the recommendation performance of target domains based on domain-shared information. Recent research considers domain-invariant and domain-specific features. Nevertheless, these intricately entangled features are hardly discerned for differentiation and the semantic diversity in heterogeneous relationships tends to be understated. In light of this, a novel model entitled Disentangled Representations for Cross-Domain Recommendation via Heterogeneous Graph Contrastive Learning (DHCL) is proposed. We derive domain-invariant and domain-specific representations, capturing both commonalities and unique features across diverse domains. Heterogeneous graph and meta-path are used to assist in enhancing the amount of information. We formulate dual contrastive learning tasks to further obtain optimal disentangled representations. Comprehensive experiments on three pairs of authentic review datasets highlight the superiority of DHCL over SOTA recommendation methods.
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
Similar content being viewed by others
References
Yin H, Wang Q, et al.: Overcoming data sparsity in group recommendation. In: TKDE, 34(7), pp. 3447-3460 (2020).
Zhu F, Wang Y, et al.: Cross-domain recommendation: challenges, progress, and prospects. arXiv Preprint arXiv:2103.01696 (2021).
Zang T, Zhu Y, et al.: A survey on cross-domain recommendation: taxonomies, methods, and future directions. In: TOIS, 41(2), pp. 1-39(2022).
Zhang R, Zang T, et al.: Disentangled contrastive learning for cross-domain recommendation. In: DASFAA, pp. 163-178 (2023).
Xin Wang, et al.: Disentangled representation learning for recommendation. In: TPAMI, pp. 408-424 (2022).
Zhu F, Chen C, et al.: Dtcdr: A framework for dual-target cross-domain recommendation. In: CIKM, pp. 1533-1542 (2019).
Zhu Y, Tang Z, et al.: Personalized transfer of user preferences for cross-domain recommendation. In: WSDM, pp. 1507-1515 (2022).
Chen M, et al.: HGCL: Heterogeneous graph contrastive learning for recommendation. In: WSDM, pp. 544-552 (2023).
He X, Liao L, Zhang H, Nie L, Hu X, et al. Neural collaborative filtering. In: WWW, pp. 173-182 (2017).
Zhang C, Song D, Huang C, Swami Ananthram, et al.: Heterogeneous graph neural network. In: KDD, pp. 793-803 (2019).
Yu J, Yin H, et al. Are graph augmentations necessary? simple graph contrastive learning for recommendation. In: SIGIR pp. 1294-1303 (2022).
Guo L, Lu Z, Yu J, et al.: Prompt-enhanced federated content representation learning for cross-domain recommendation. arXiv preprint arXiv:2401.14678, 2024.
Hao B, Yang C, Guo L, et al.: Motif-based prompt learning for universal cross-domain recommendation. In: WSDM, pp. 257-265 (2024).
Liu H, Guo L, Zhu L, et al.: MCRPL: A Pretrain, prompt, and fine-tune paradigm for non-overlapping many-to-one cross-domain recommendation. In: TOIS, pp. 1-24 (2024).
Guo L, Zhang J, Tang L, et al.: Time interval-enhanced graph neural network for shared-account cross-domain sequential recommendation. In: TNNLs, pp. 4002 - 4016 (2023).
Guo L, Zhang J, Chen T, et al.: Reinforcement learning-enhanced shared-account cross-domain sequential recommendation. In: TKDE, pp. 7397 - 7411 (2022).
Liu Y, Xuan H, Li B, et al.: Self-Supervised Dynamic Hypergraph Recommendation based on Hyper-Relational Knowledge Graph. In: CIKM, pp. 1617-1626 (2023).
Yan H, Chen X, Gao C, et al.: Deepapf: Deep attentive probabilistic factorization for multi-site video recommendation. In: IJCAI, pp. 17-883 (2019).
Singh A P, Gordon G J. Relational learning via collective matrix factorization. In: SIGKDD, pp. 650-658 (2008).
Hu G, Zhang Y, Yang Q. Conet: Collaborative cross networks for cross-domain recommendation. In: CIKM, pp. 667-676 (2018).
Yu X, Peng Q, et al.: A selective ensemble learning based two-sided cross-domain collaborative filtering algorithm. In: IPM, 58(6), 102691 (2021).
Liu M, Li J, et al.: Bi-TGCF: Cross domain recommendation via bi-directional transfer graph collaborative filtering networks. In: CIKM, pp. 885-894 (2020).
Li P, Tuzhilin A, et al.: Ddtcdr: Deep dual transfer cross domain recommendation. In: WSDM, pp. 331-339 (2020).
Zhao C, Li C, et al.: Cross-domain recommendation via preference propagation graphNet. In: CIKM, pp. 2165-2168 (2019).
Z X, et al.: Multi-sparse-domain collaborative recommendation via enhanced comprehensive aspect preference learning. In: WSDM, pp. 1452-60 (2022).
Cui Q, Wei T, et al.: HeroGRAPH: A heterogeneous graph framework for multi-target cross-domain recommendation. In: RecSys (2020).
Wu J, Wang X, et al.: Self-supervised graph learning for recommendation. In: SIGIR, pp. 726-735 (2021).
Wang X, Jin H, Zhang A, et al.: Disentangled graph collaborative filtering. In: SIGIR, pp. 1001-1010 (2020).
Jianxin Ma, et al.: Learning disentangled representations for recommendation. In NeurIPS, pp. 5711-5722 (2019).
Xiao, S., Zhu, D., Tang, C. et al.: Combining Graph Contrastive Embedding and Multi-head Cross-Attention Transfer for Cross-Domain Recommendation. Data Sci. Eng. 8, 247-262 (2023).
Xuan H, Liu Y, Li B, et al.: Knowledge enhancement for contrastive multi-behavior recommendation. In: WSDM, pp. 195-203 (2023).
Yu J, Xia X., et al.: XSimGCL: Towards extremely simple graph contrastive learning for recommendation. In: TKDE (2023).
Li A, Zang Y, Wang Y, et al.: Leveraging Interactive Paths for Sequential Recommendation. In: DASFAA, pp. 521-536 (2023).
Xia X, Yin H, et al.: Self-supervised hypergraph convolutional networks for session-based recommendation. In: AAAI, vol. 35(5), pp. 4503-4511 (2021).
Z K, et al.: S3-Rec: Self-supervised learning for sequential recommendation with mutual information maximization. In: ICKM, pp. 1893-1902 (2020).
Yang Y, Huang C, et al.: Knowledge graph contrastive learning for recommendation. In: SIGIR, pp. 1434-1443 (2022).
He X, Deng K, et al.: Lightgcn: Simplifying and powering graph convolution network for recommendation. In: SIGIR, pp. 639-648 (2020).
Acknowledgement
This work is supported in part by the "14th Five-Year Plan" Civil Aerospace Pre-Research Project of China under Grant No. D020101, the Natural Science Foundation of China No. 62302213, Innovation Funding of Key Laboratory of Intelligent Decision and Digital Operations No. NJ2023027, Ministry of Industrial and Information Technology Project of Hebei Key Laboratory of Software Engineering, No. 22567637H, the Natural Science Foundation of Jiangsu Province under Grant No. BK20210280.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2025 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Liu, X., Li, B., Chen, Y., Li, X., Xu, S., Yin, H. (2025). Disentangled Representations for Cross-Domain Recommendation via Heterogeneous Graph Contrastive Learning. In: Onizuka, M., et al. Database Systems for Advanced Applications. DASFAA 2024. Lecture Notes in Computer Science, vol 14852. Springer, Singapore. https://doi.org/10.1007/978-981-97-5555-4_3
Download citation
DOI: https://doi.org/10.1007/978-981-97-5555-4_3
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-5554-7
Online ISBN: 978-981-97-5555-4
eBook Packages: Computer ScienceComputer Science (R0)