Cross-Domain Recommendation for Cold-Start Users via Neighborhood Based Feature Mapping

  • Xinghua Wang
  • Zhaohui Peng
  • Senzhang Wang
  • Philip S. Yu
  • Wenjing Fu
  • Xiaoguang Hong
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10827)


Traditional Collaborative Filtering (CF) models mainly focus on predicting a user’s preference to the items in a single domain such as the movie domain or the music domain. A major challenge for such models is the data sparsity problem, and especially, CF cannot make accurate predictions for the cold-start users who have no ratings at all. Although Cross-Domain Collaborative Filtering (CDCF) is proposed for effectively transferring users’ rating preference across different domains, it is still difficult for existing CDCF models to tackle the cold-start users in the target domain due to the extreme data sparsity. In this paper, we propose a Cross-Domain Latent Feature Mapping (CDLFM) model for cold-start users in the target domain. Firstly, the user rating behavior is taken into consideration in the matrix factorization for alleviating the data sparsity. Secondly, neighborhood based latent feature mapping is proposed to transfer the latent features of a cold-start user from the auxiliary domain to the target domain. Extensive experiments on two real datasets extracted from Amazon transaction data demonstrate the superiority of our proposed model against other state-of-the-art methods.


Cross-domain recommendation Cold start Feature mapping 



This work is supported by NSF of China (No. 61602237, No. 61672313), 973 Program (No. 2015CB352501), NSF of Shandong, China (No. ZR2017MF065), NSF of Jiangsu, China (No. BK20171420). This work is also supported by US NSF through grants IIS-1526499, and CNS-1626432.


  1. 1.
    Pan, W., Yang, Q.: Transfer learning in heterogeneous collaborative filtering domains. Artif. Intell. 197, 39–55 (2013)MathSciNetCrossRefGoogle Scholar
  2. 2.
    Pan, W., Xiang, E.W., Liu, N.N., Yang, Q.: Transfer learning in collaborative filtering for sparsity reduction. In: AAAI, pp. 230–235 (2010)Google Scholar
  3. 3.
    Singh, A.P., Gordon, G.J.: Relational learning via collective matrix factorization. In: KDD, pp. 650–658 (2008)Google Scholar
  4. 4.
    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.
  5. 5.
    Salakhutdinov, R., Mnih, A.: Probabilistic matrix factorization. In: NIPS, pp. 1257–1264 (2007)Google Scholar
  6. 6.
    Koren, Y.: Factorization meets the neighborhood: a multifaceted collaborative filtering model. In: KDD, pp. 426–434 (2008)Google Scholar
  7. 7.
    Zhen, Y., Li, W.J., Yeung, D.Y.: TagiCoFi: tag informed collaborative filtering. In: RecSys, pp. 69–76 (2009)Google Scholar
  8. 8.
    Fernández-Tobías, I., Cantador, I.: Exploiting social tags in matrix factorization models for cross-domain collaborative filtering. In: CBRecSys@RecSys, pp. 34–41 (2014)Google Scholar
  9. 9.
    Song, T., Peng, Z., Wang, S., Fu, W., Hong, X., Yu, P.S.: Review-based cross-domain recommendation through joint tensor factorization. In: Candan, S., Chen, L., Pedersen, T.B., Chang, L., Hua, W. (eds.) DASFAA 2017. LNCS, vol. 10177, pp. 525–540. Springer, Cham (2017). Scholar
  10. 10.
    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)Google Scholar
  11. 11.
    Man, T., Shen, H., Jin, X., Cheng, X.: Cross-domain recommendation: an embedding and mapping approach. In: IJCAI, pp. 2464–2470 (2017)Google Scholar
  12. 12.
    Kazama, M., Varga, I.: Cross domain recommendation using vector space transfer learning. In: RecSys Posters (2016)Google Scholar
  13. 13.
    Wang, S., Hu, X., Yu, P.S., Li, Z.: MMRate: inferring multi-aspect diffusion networks with multi-pattern cascades. In: KDD, pp. 1246–1255 (2014)Google Scholar
  14. 14.
    Zhao, W.X., Li, S., He, Y., Chang, E.Y., Wen, J.R., Li, X.: Connecting social media to e-commerce: cold-start product recommendation using microblogging information. IEEE Trans. Knowl. Data Eng. 28(5), 1147–1159 (2016)CrossRefGoogle Scholar
  15. 15.
    Friedman, J.H.: Greedy function approximation: a gradient boosting machine. Ann. Statist. 29, 1189–1232 (2000)MathSciNetCrossRefGoogle Scholar
  16. 16.
    He, R., McAuley, J.: Ups and downs: modeling the visual evolution of fashion trends with one-class collaborative filtering. In: WWW, pp. 507–517 (2016)Google Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  • Xinghua Wang
    • 1
  • Zhaohui Peng
    • 1
  • Senzhang Wang
    • 2
  • Philip S. Yu
    • 3
    • 4
  • Wenjing Fu
    • 1
  • Xiaoguang Hong
    • 1
  1. 1.School of Computer Science and TechnologyShandong UniversityJinanChina
  2. 2.College of Computer Science and TechnologyNanjing University of Aeronautics and AstronauticsNanjingChina
  3. 3.Department of Computer ScienceUniversity of Illinois at ChicagoChicagoUSA
  4. 4.Institute for Data ScienceTsinghua UniversityBeijingChina

Personalised recommendations