Local Top-N Recommendation via Refined Item-User Bi-Clustering
Top-\(N\) recommendation has drawn much attention from many portal websites nowadays. The classic item-based methods based on sparse linear models (SLIM) have demonstrated very good performance, which estimate a single model for all users. Lately, local models have been considered necessary since a user only resembles a group of others but not all. Moreover, we find that two users with similar tastes on one item group may have totally different tastes on another. Thus, it is intuitive to make preference predictions for a user via item-user subgroups rather than the entire feedback matrix. For elegant local top-\(N\) recommendation, this paper introduces a bi-clustering scheme to be integrated with SLIM, such that item-user subgroups are softly constructed to capture subtle preferences of users. A novel localized recommendation model is hence presented, and an alternative direction algorithm is devised to collectively learn item coefficient for each local model. To deal with the data sparsity issue during clustering, we conceive a refined feature-based distance measure to better model and reflect user-item interaction. The proposed method is experimentally compared with state-of-the-art methods, and the results demonstrate the superiority of our model.
This work was partially supported by NSFC under grants Nos. 61402494, 61402498, 71690233, NSF Hunan under grant No. 2015JJ4009, and ARC under grants DP150103071, DP150102728.
- 1.Aiolli, F.: A preliminary study on a recommender system for the million songs dataset challenge. In: Italian Information Retrieval Workshop, pp. 73–83 (2013)Google Scholar
- 2.Chen, Y., Zhao, X., de Rijke, M.: Top-\(N\) recommendation with high-dimensional side information via locality preserving projection. In: SIGIR, pp. 985–988 (2017)Google Scholar
- 3.Cremonesi, P., Koren, Y., Turrin, R.: Performance of recommender algorithms on top-\(N\) recommendation tasks. In: RecSys, pp. 39–46 (2010)Google Scholar
- 5.George, T., Merugu, S.: A scalable collaborative filtering framework based on co-clustering. In: ICDM, pp. 625–628 (2005)Google Scholar
- 6.Hofmann, T., Puzicha, J.: Latent class models for collaborative filtering. In: IJCAI, pp. 688–693 (1999)Google Scholar
- 7.Kabbur, S., Ning, X., Karypis, G.: FISM: factored item similarity models for top-\(N\) recommender systems. In: SIGKDD, pp. 659–667 (2013)Google Scholar
- 8.Karypis, G.: Evaluation of item-based top-\(N\) recommendation algorithms. In: CIKM, pp. 247–254 (2001)Google Scholar
- 9.Lee, J., Kim, S., Lebanon, G., Singer, Y.: Local low-rank matrix approximation. In: ICML, pp. 82–90 (2013)Google Scholar
- 10.Lee, J., Bengio, S., Kim, S., Lebanon, G., Singer, Y.: Local collaborative ranking. In: WWW, pp. 85–96 (2014)Google Scholar
- 11.Ning, X., Karypis, G.: SLIM: sparse linear methods for top-\(N\) recommender systems. In: IEEE ICDM, pp. 497–506 (2011)Google Scholar
- 12.O’Connor, M., Jon Herlocker, J.: Clustering items for collaborative filtering. In: SIGIR Workshops on Recommender Systems (1999)Google Scholar
- 13.Ungar, L.H., Foster, D.P.: Clustering methods for collaborative filtering. In: AAAI Workshops on Recommender Systems, pp. 114–129 (1998)Google Scholar
- 14.Xu, B., Bu, J., Chen, C., Cai, D.: An exploration of improving collaborative recommender systems via user-item subgroups. In: WWW, pp. 21–30 (2012)Google Scholar