Skip to main content
Springer Nature Link
Log in

Explicitly modeling relationships between domain-specific and domain-invariant interests for cross-domain recommendation

  • Published:
World Wide Web Aims and scope Submit manuscript

Abstract

This paper focuses on cross-domain recommendation (CDR) without auxiliary information. Existing works on CDR all ignore the bi-directional transformation relationships between users’ domain-invariant interests and domain-specific interests. Moreover, they only rely on the sparse interactions as supervised signals for model training, which can not guarantee the generated representations are effective. In response to the limitation of these existing works, we propose a model named MRCDR which explicitly models relationships between domain-specific and domain-invariant interests for cross-domain recommendation. We project the domain-specific representations of users to a common space generating their domain-invariant representations. To remedy the problem of insufficient supervised signals, we propose two strategies that generate extra self-supervision signals to enhance model training. The aligned strategy tries to make the two domain-invariant representations an overlapped user to be consistent. The cycle strategy tries to make the reversely projected representation of the domain-invariant representation of a non-overlapped user to be consistent with its original domain-specific representation. We conduct extensive experiments on real-world datasets and the results show the effectiveness of our proposed model against the state-of-the-art methods.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Similar content being viewed by others

Availability of supporting data

The Amazon dataset used in this paper is downloaded from http://jmcauley.ucsd.edu/data/amazon/.The Douban dataset used in this paper is crawled from the Douban website https://www.douban.com and is available at https://github.com/zangtianzi/Douban Dataset.

Notes

  1. http://jmcauley.ucsd.edu/data/amazon/

  2. https://www.douban.com

  3. https://github.com/zangtianzi/Douban_Dataset

  4. We will release the code in the future.

References

  1. Man, T., Shen, H., Jin, X., Cheng, X.: Cross-domain recommendation: an embedding and mapping approach. In: IJCAI, pp. 2464–2470 (2017)

  2. Wang, X., Peng, Z., Wang, S., Yu, P.S., Fu, W., Hong, X.: Cross-domain recommendation for cold-start users via neighborhood based feature mapping. In: DASFAA, vol. 10827, pp. 158–165 (2018)

  3. Fu, W., Peng, Z., Wang, S., Xu, Y., Li, J.: Deeply fusing reviews and contents for cold start users in cross-domain recommendation systems. In: AAAI, pp. 94–101 (2019)

  4. Wang, T., Zhuang, F., Zhang, Z., Wang, D., Zhou, J., He, Q.: Low-dimensional alignment for cross-domain recommendation. In: CIKM, pp. 3508–3512 (2021)

  5. Singh, A.P., Gordon, G.J.: Relational learning via collective matrix factorization. In: SIGKDD, pp. 650–658 (2008)

  6. Hu, G., Zhang, Y., Yang, Q.: Conet: Collaborative cross networks for cross-domain recommendation. In: CIKM, pp. 667–676 (2018)

  7. Liu, J., Zhao, P., Zhuang, F., Liu, Y., Sheng, V.S., Xu, J., Zhou, X., Xiong, H.: Exploiting aesthetic preference in deep cross networks for cross-domain recommendation. In: WWW, pp. 2768–2774 (2020)

  8. 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)

  9. Elkahky, A.M., Song, Y., He, X.: A multi-view deep learning approach for cross domain user modeling in recommendation systems. In: WWW, pp. 278–288 (2015)

  10. Lian, J., Zhang, F., Xie, X., Sun, G.: Cccfnet: a content-boosted collaborative filtering neural network for cross domain recommender systems. In: WWW companion, pp. 817–818 (2017)

  11. Zhao, C., Li, C., Fu, C.: Cross-domain recommendation via preference propagation graphnet. In: CIKM, pp. 2165–2168 (2019)

  12. Li, P., Tuzhilin, A.: DDTCDR: deep dual transfer cross domain recommendation. In: WSDM, pp. 331–339 (2020)

  13. Yan, H., Chen, X., Gao, C., Li, Y., Jin, D.: Deepapf: Deep attentive probabilistic factorization for multi-site video recommendation. In: IJCAI, pp. 1459–1465 (2019)

  14. Xu, K., Xie, Y., Chen, L., Zheng, Z.: Expanding relationship for cross domain recommendation. In: CIKM, pp. 2251–2260 (2021)

  15. Chen, C., Zhang, M., Wang, C., Ma, W., Li, M., Liu, Y., Ma, S.: An efficient adaptive transfer neural network for social-aware recommendation. In: SIGIR, pp. 225–234 (2019)

  16. 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)

  17. Zang, T., Zhu, Y., Zhang, R., Wang, C., Wang, K., Yu, J.: Contrastive multi-view interest learning for cross-domain sequential recommendation. ACM Trans. Inf. Syst. (2023)

  18. Shang, M., Li, P., Fu, Z., Bing, L., Zhao, D., Shi, S., Yan, R.: Semi-supervised text style transfer: Cross projection in latent space. In: EMNLP-IJCNLP, pp. 4936–4945 (2019)

  19. John, V., Mou, L., Bahuleyan, H., Vechtomova, O.: Disentangled representation learning for non-parallel text style transfer. In: ACL, pp. 424–434 (2019)

  20. Shen, T., Lei, T., Barzilay, R., Jaakkola, T.S.: Style transfer from non-parallel text by cross-alignment. In: NIPS, pp. 6830–6841 (2017)

  21. 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. lecture notes in computer science, vol. 13246, pp. 53–68 (2022)

  22. Ding, Y., Li, H., Chen, K., Shou, L.: TPUF: enhancing cross-domain sequential recommendation via transferring pre-trained user features. In: CIKM, pp. 410–419 (2023)

  23. Cao, J., Cong, X., Sheng, J., Liu, T., Wang, B.: Contrastive cross-domain sequential recommendation. In: CIKM, pp. 138–147 (2022)

  24. Chen, M., Huang, C., Xia, L., Wei, W., Xu, Y., Luo, R.: Heterogeneous graph contrastive learning for recommendation. In: WSDM, pp. 544–552 (2023)

  25. Xie, R., Liu, Q., Wang, L., Liu, S., Zhang, B., Lin, L.: Contrastive cross-domain recommendation in matching. In: KDD, pp. 4226–4236 (2022)

  26. Yang, W., Yang, J., Liu, Y.: Multimodal optimal transport knowledge distillation for cross-domain recommendation. In: CIKM, pp. 2959–2968 (2023)

  27. Xu, Z., Pan, W., Ming, Z.: A multi-view graph contrastive learning framework for cross-domain sequential recommendation. In: RecSys, pp. 491–501 (2023)

  28. Kang, S., Hwang, J., Lee, D., Yu, H.: Semi-supervised learning for cross-domain recommendation to cold-start users. In: CIKM, pp. 1563–1572 (2019)

  29. Liu, W., Zheng, X., Su, J., Hu, M., Tan, Y., Chen, C.: Exploiting variational domain-invariant user embedding for partially overlapped cross domain recommendation. In: SIGIR, ACM, pp. 312–321 (2022)

  30. Zhao, C., Zhao, H., He, M., Zhang, J., Fan, J.: Cross-domain recommendation via user interest alignment. In: WWW, ACM, pp. 887–896 (2023)

  31. Zhu, F., Wang, Y., Chen, C., Liu, G., Orgun, M.A., Wu, J.: A deep framework for cross-domain and cross-system recommendations. In: IJCAI, pp. 3711–3717 (2018)

  32. Bi, Y., Song, L., Yao, M., Wu, Z., Wang, J., Xiao, J.: DCDIR: a deep cross-domain recommendation system for cold start users in insurance domain. In: SIGIR, pp. 1661–1664 (2020)

  33. Bi, Y., Song, L., Yao, M., Wu, Z., Wang, J., Xiao, J.: A heterogeneous information network based cross domain insurance recommendation system for cold start users. In: SIGIR, pp. 2211–2220 (2020)

  34. 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), 42–14239 (2023)

    Article  Google Scholar 

  35. Pan, W., Liu, N.N., Xiang, E.W., Yang, Q.: Transfer learning to predict missing ratings via heterogeneous user feedbacks. In: IJCAI, pp. 2318–2323 (2011)

  36. Li, B., Yang, Q., Xue, X.: Can movies and books collaborate? cross-domain collaborative filtering for sparsity reduction. In: IJCAI, pp. 2052–2057 (2009)

  37. Gao, S., Luo, H., Chen, D., Li, S., Gallinari, P., Guo, J.: Cross-domain recommendation via cluster-level latent factor model. In: ECML PKDD, vol. 8189, pp. 161–176 (2013)

  38. Hu, L., Cao, J., Xu, G., Cao, L., Gu, Z., Zhu, C.: Personalized recommendation via cross-domain triadic factorization. In: WWW, pp. 595–606 (2013)

  39. Song, T., Peng, Z., Wang, S., Fu, W., Hong, X., Yu, P.S.: Review-based cross-domain recommendation through joint tensor factorization. In: DASFAA, vol. 10177, pp. 525–540 (2017)

  40. Li, P., Jiang, Z., Que, M., Hu, Y., Tuzhilin, A.: Dual attentive sequential learning for cross-domain click-through rate prediction. In: SIGKDD, pp. 3172–3180 (2021)

  41. Yuan, F., Yao, L., Benatallah, B.: Darec: deep domain adaptation for cross-domain recommendation via transferring rating patterns. In: IJCAI, pp. 4227–4233 (2019)

  42. Liu, J., Sun, L., Nie, W., Jing, P., Su, Y.: Graph disentangled contrastive learning with personalized transfer for cross-domain recommendation. In: AAAI, AAAI Press, pp. 8769–8777 (2024)

  43. 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)

  44. 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)

  45. Zhao, C., Li, C., Xiao, R., Deng, H., Sun, A.: CATN: cross-domain recommendation for cold-start users via aspect transfer network. In: SIGIR, pp. 229–238 (2020)

  46. Lu, J., Sun, G., Fang, X., Yang, J., He, W.: A contrastive learning framework for dual-target cross-domain recommendation. In: MM, ACM, pp. 6332–6339 (2023)

  47. Zhu, J., Wang, Y., Zhu, F., Sun, Z.: Domain disentanglement with interpolative data augmentation for dual-target cross-domain recommendation. In: RecSys, ACM, pp. 515–527 (2023)

  48. Li, Z., Amagata, D., Zhang, Y., Hara, T., Haruta, S., Yonekawa, K., Kurokawa, M.: Mutual information-based preference disentangling and transferring for non-overlapped multi-target cross-domain recommendations. In: SIGIR, ACM, pp. 2124–2133 (2024)

  49. Ouyang, Y., Guo, B., Tang, X., He, X., Xiong, J., Yu, Z.: Learning cross-domain representation with multi-graph neural network. CoRR (2019)

  50. Xi, D., Zhuang, F., Zhu, Y., Zhao, P., Zhang, X., He, Q.: Graph factorization machines for cross-domain recommendation. CoRR (2020)

  51. Haris, M., Shakhnarovich, G., Ukita, N.: Recurrent back-projection network for video super-resolution. In: CVPR, pp. 3897–3906 (2019)

  52. Zhang, Y., Liu, Y., Han, P., Miao, C., Cui, L., Li, B., Tang, H.: Learning personalized itemset mapping for cross-domain recommendation. In: IJCAI, pp. 2561–2567 (2020)

  53. He, X., He, Z., Du, X., Chua, T.: Adversarial personalized ranking for recommendation. In: SIGIR, pp. 355–364 (2018)

  54. Wang, X., He, X., Wang, M., Feng, F., Chua, T.: Neural graph collaborative filtering. In: SIGIR, pp. 165–174 (2019)

  55. He, X., Liao, L., Zhang, H., Nie, L., Hu, X., Chua, T.: Neural collaborative filtering. In: WWW, pp. 173–182 (2017)

  56. Perera, D., Zimmermann, R.: LSTM networks for online cross-network recommendations. In: Lang, J. (ed.) IJCAI, pp. 3825–3833 (2018)

  57. Guo, L., Tang, L., Chen, T., Zhu, L., Nguyen, Q.V.H., Yin, H.: DA-GCN: A domain-aware attentive graph convolution network for shared-account cross-domain sequential recommendation. In: IJCAI, pp. 2483–2489 (2021)

  58. Chen, C., Guo, J., Song, B.: Dual attention transfer in session-based recommendation with multi-dimensional integration. In: SIGIR, pp. 869–878 (2021)

Download references

Acknowledgements

We thank each of the authors for their contributions to this paper, and everyone who is not listed as an author but has helped to revise this manuscript.

Funding

This research is supported in part by National Science Foundation of China (No. 62472277, No. 62072304, No.62172275, No.62472176, No. 62202224), China Postdoctoral Science Foundation under Grant Number 2023M741685, 2022TQ0154, Natural Science Foundation of Jiangsu Province under Grant No. BK20220882, Shanghai Municipal Science and Technology Commission (No. 21511104700), and the Shanghai East Talents Program (2023-177).

Author information

Authors and Affiliations

  1. College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, 29 Jiangjun Avenue, Jiangning District, Nanjing City, Jiangsu Province, China

    Tianzi Zang

  2. School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Dongchuan Road, Shanghai, 200240, Shanghai, China

    Yanmin Zhu, Ruohan Zhang & Feilong Tang

  3. Alibaba Group, Hangzhou, 310000, Zhejiang, China

    Jing Zhu

Authors
  1. Tianzi Zang
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Yanmin Zhu
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Ruohan Zhang
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Jing Zhu
    View author publications

    You can also search for this author inPubMed Google Scholar

  5. Feilong Tang
    View author publications

    You can also search for this author inPubMed Google Scholar

Contributions

Tianzi Zang designed this method and wrote the main manuscript text. Yanmin Zhu sponsored the research. Ruohan Zhang conducted experiments and prepared Tables 1-3. Jing Zhu gave advice on writing and helped with preparing figures. Feilong Tang reviewed the manuscript.

Corresponding author

Correspondence to Yanmin Zhu.

Ethics declarations

Competing interests

The authors declare no competing interests.

Ethical Approval and Consent to participate

Not applicable.

Human and Animal Ethics

Not applicable.

Consent for publication

All authors whose names appear on the submission1) made substantial contributions to the conception or design of the work; or the acquisition, analysis, or interpretation of data; or the creation of new software used in the work;2) drafted the work or revised it critically for important intellectual content;3) approved the version to be published; and4) agree to be accountable for all aspects of the work in ensuring that questions related to the accuracy or integrity of any part of the work are appropriately investigated and resolved.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zang, T., Zhu, Y., Zhang, R. et al. Explicitly modeling relationships between domain-specific and domain-invariant interests for cross-domain recommendation. World Wide Web 27, 73 (2024). https://doi.org/10.1007/s11280-024-01305-z

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s11280-024-01305-z

Keywords