TY - GEN
T1 - Collaborative filtering with collective training
AU - Ge, Yong
AU - Xiong, Hui
AU - Tuzhilin, Alexander
AU - Liu, Qi
PY - 2011
Y1 - 2011
N2 - Rating sparsity is a critical issue for collaborative filtering. For example, the well-known Netflix Movie rating data contain ratings of only about 1% user-item pairs. One way to address this rating sparsity problem is to develop more effective methods for training rating prediction models. To this end, in this paper, we introduce a collective training paradigm to automatically and effectively augment the training ratings. Essentially, the collective training paradigm builds multiple different Collaborative Filtering (CF) models separately, and augments the training ratings of each CF model by using the partial predictions of other CF models for unknown ratings. Along this line, we develop two algorithms, Bi-CF and Tri-CF, based on collective training. For Bi-CF and Tri-CF, we collectively and iteratively train two and three different CF models via iteratively augmenting training ratings for individual CF model. We also design different criteria to guide the selection of augmented training ratings for Bi-CF and Tri-CF. Finally, the experimental results show that Bi-CF and Tri-CF algorithms can significantly outperform baseline methods, such as neighborhood-based and SVD-based models.
AB - Rating sparsity is a critical issue for collaborative filtering. For example, the well-known Netflix Movie rating data contain ratings of only about 1% user-item pairs. One way to address this rating sparsity problem is to develop more effective methods for training rating prediction models. To this end, in this paper, we introduce a collective training paradigm to automatically and effectively augment the training ratings. Essentially, the collective training paradigm builds multiple different Collaborative Filtering (CF) models separately, and augments the training ratings of each CF model by using the partial predictions of other CF models for unknown ratings. Along this line, we develop two algorithms, Bi-CF and Tri-CF, based on collective training. For Bi-CF and Tri-CF, we collectively and iteratively train two and three different CF models via iteratively augmenting training ratings for individual CF model. We also design different criteria to guide the selection of augmented training ratings for Bi-CF and Tri-CF. Finally, the experimental results show that Bi-CF and Tri-CF algorithms can significantly outperform baseline methods, such as neighborhood-based and SVD-based models.
KW - collaborative filtering
KW - collective training
UR - http://www.scopus.com/inward/record.url?scp=82555191349&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=82555191349&partnerID=8YFLogxK
U2 - 10.1145/2043932.2043983
DO - 10.1145/2043932.2043983
M3 - Conference contribution
AN - SCOPUS:82555191349
SN - 9781450306836
T3 - RecSys'11 - Proceedings of the 5th ACM Conference on Recommender Systems
SP - 281
EP - 284
BT - RecSys'11 - Proceedings of the 5th ACM Conference on Recommender Systems
T2 - 5th ACM Conference on Recommender Systems, RecSys 2011
Y2 - 23 October 2011 through 27 October 2011
ER -