Make Users and Preferred Items Closer: Recommendation via Distance Metric Learning
Recommender systems can help to relieve the dilemma called information overload. Collaborative filtering is a primary approach based on collective historical ratings to recommend items to users. One of the most competitive collaborative filtering algorithm is matrix factorization. In this paper, we proposed an alternative method. It aims to make users be spatially close to items they like and be far away from items they dislike, by connecting matrix factorization and distance metric learning. The metric and latent factors are trained simultaneously and then used to generate reliable recommendations. The experiments conducted on the real-world datasets have shown that, compared with methods only based on factorization, our method has advantage in terms of accuracy.
KeywordsRecommendation Distance metric learning Collaborative filtering Matrix factorization
This research is supported by the Basic and Advanced Research Projects in Chongqing (cstc2015jcyjA40049), the National Key Basic Research Program of China (973) (2013CB328903), the National Natural Science Foundation of China (61472021), and the Fundamental Research Funds for the Central Universities (106112014 CDJZR 095502).
- 2.Hocke, J., Martinetz, T.: Global metric learning by gradient descent. In: Wermter, S., Weber, C., Duch, W., Honkela, T., Koprinkova-Hristova, P., Magg, S., Palm, G., Villa, A.E.P. (eds.) ICANN 2014. LNCS, vol. 8681, pp. 129–135. Springer, Cham (2014). doi: 10.1007/978-3-319-11179-7_17 Google Scholar
- 3.Hsieh, C.K., Yang, L., Cui, Y., Lin, T.Y.: Collaborative metric learning. In: Proceedings of the 26th International Conference on World Wide Web, pp. 193–201. ACM (2017)Google Scholar
- 4.Jamali, M., Ester, M.: A matrix factorization technique with trust propagation for recommendation in social networks, pp. 135–142 (2010)Google Scholar
- 5.Khoshneshin, M., Street, W.N.: Collaborative filtering via Euclidean embedding. In: ACM Conference on Recommender Systems, pp. 87–94 (2010)Google Scholar
- 8.Kulis, B., et al.: Metric learning: a survey. Found. Trends \(\textregistered \). Mach. Learn. 5(4), 287–364 (2013). Now Publishers, Inc.Google Scholar
- 12.Salakhutdinov, R., Mnih, A.: Probabilistic matrix factorization. In: International Conference on Neural Information Processing Systems, pp. 1257–1264 (2007)Google Scholar