TY - GEN
T1 - Discrete content-aware matrix factorization
AU - Lian, Defu
AU - Liu, Rui
AU - Ge, Yong
AU - Zheng, Kai
AU - Xie, Xing
AU - Cao, Longbing
N1 - Funding Information:
The work is supported by the National Natural Science Foundation of China (61502077,61631005,61602234,61572032,61502324,61532018) and the Fundamental Research Funds for the Central Universities (ZYGX2014Z012, ZYGX2016J087).
Publisher Copyright:
© 2017 ACM.
PY - 2017/8/13
Y1 - 2017/8/13
N2 - Precisely recommending relevant items from massive candidates to a large number of users is an indispensable yet computationally expensive task in many online platforms (e.g., Amazon.com and Netfix.com). A promising way is to project users and items into a Hamming space and then recommend items via Hamming distance. However, previous studies didn't address the cold-start challenges and couldn't make the best use of preference data like implicit feedback. To fill this gap, we propose a Discrete Content-aware Matrix Factorization (DCMF) model, 1) to derive compact yet informative binary codes at the presence of user/item content information; 2) to support the classification task based on a local upper bound of logit loss; 3) to introduce an interaction regularization for dealing with the sparsity issue. We further develop an eficient discrete optimization algorithm for parameter learning. Based on extensive experiments on three real-world datasets, we show that DCFM outperforms the state-of-the-arts on both regression and classification tasks.
AB - Precisely recommending relevant items from massive candidates to a large number of users is an indispensable yet computationally expensive task in many online platforms (e.g., Amazon.com and Netfix.com). A promising way is to project users and items into a Hamming space and then recommend items via Hamming distance. However, previous studies didn't address the cold-start challenges and couldn't make the best use of preference data like implicit feedback. To fill this gap, we propose a Discrete Content-aware Matrix Factorization (DCMF) model, 1) to derive compact yet informative binary codes at the presence of user/item content information; 2) to support the classification task based on a local upper bound of logit loss; 3) to introduce an interaction regularization for dealing with the sparsity issue. We further develop an eficient discrete optimization algorithm for parameter learning. Based on extensive experiments on three real-world datasets, we show that DCFM outperforms the state-of-the-arts on both regression and classification tasks.
KW - Collaborative filtering
KW - Content-based filtering
KW - Discrete hashing
KW - Recommendation
UR - http://www.scopus.com/inward/record.url?scp=85029047321&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85029047321&partnerID=8YFLogxK
U2 - 10.1145/3097983.3098008
DO - 10.1145/3097983.3098008
M3 - Conference contribution
AN - SCOPUS:85029047321
T3 - Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
SP - 325
EP - 334
BT - KDD 2017 - Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
PB - Association for Computing Machinery
T2 - 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2017
Y2 - 13 August 2017 through 17 August 2017
ER -