{"type":"ScholarlyArticle","title":"Incremental Matrix Factorization: A Linear Feature Transformation Perspective","authors":[{"name":"Xunpeng Huang","slug":"xunpeng-huang","given":"Xunpeng","family":"Huang","affiliation":"† Anhui Province Key Lab. of Big Data Analysis and Application , University of S&T of China"},{"name":"Le Wu","slug":"le-wu","given":"Le","family":"Wu","affiliation":"‡ School of Computer and Information , HeFei University of Technology Baidu Talent Intelligence Center"},{"name":"Enhong Chen","slug":"enhong-chen","given":"Enhong","family":"Chen","affiliation":"† Anhui Province Key Lab. of Big Data Analysis and Application , University of S&T of China"},{"name":"Hengshu Zhu","slug":"hengshu-zhu","given":"Hengshu","family":"Zhu","affiliation":""},{"name":"Qi Liu","slug":"qi-liu","given":"Qi","family":"Liu","affiliation":"† Anhui Province Key Lab. of Big Data Analysis and Application , University of S&T of China"},{"name":"Yijun Wang","slug":"yijun-wang","given":"Yijun","family":"Wang","affiliation":"† Anhui Province Key Lab. of Big Data Analysis and Application , University of S&T of China"}],"abstract":"Matrix Factorization (MF) is among the most widely used techniques for collaborative filtering based recommendation. Along this line, a critical demand is to incrementally refine the MF models when new ratings come in an online scenario. However, most of existing incremental MF algorithms are limited by specific MF models or strict use restrictions. In this paper, we propose a general incremental MF framework by designing a linear transformation of user and item latent vectors over time. This framework shows a relatively high accuracy with a computation and space efficient training process in an online scenario. Meanwhile, we explain the framework with a low-rank approximation perspective, and give an upper bound on the training error when this framework is used for incremental learning in some special cases. Finally, extensive experimental results on two real-world datasets clearly validate the effectiveness, efficiency and storage performance of the proposed framework.","doi":"10.24963/ijcai.2017/264","url":"https://ijcai.org/proceedings/2017/264","pdf":"https://ijcai.org/proceedings/2017/0264.pdf","markdown":"https://ijcai.org/proceedings/2017/264.md","bibtex":"https://ijcai.org/proceedings/2017/bibtex/264","volume":{"slug":"2017","title":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2017","url":"https://ijcai.org/proceedings/2017/","year":2017,"location":"Melbourne, Australia","dates":"19-25 August 2017","editors":"Carles Sierra","isbn":"978-0-9992411-0-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2017"},"section":"Machine Learning A-R","track":"Main track","number":264,"pages":{"first":1901,"last":1908},"keywords":["Machine Learning: Machine Learning","Machine Learning: Time-series/Data Streams","Machine Learning: Online Learning"],"videos":[],"references":[{"position":1,"raw":"[Bach et al., 2008] Francis Bach, Julien Mairal, and Jean Ponce. Convex sparse matrix factorizations. arXiv preprint arXiv:0812.1869, 2008.","title":"Convex sparse matrix factorizations","authors":"Francis Bach, Julien Mairal, Jean Ponce","year":"2008","venue":null,"doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Brand, 2003] Matthew Brand. Fast online svd revisions for lightweight recommender systems. In SDM, pages 37-46. SIAM, 2003.","title":"Fast online svd revisions for lightweight recommender systems","authors":"Matthew Brand","year":"2003","venue":"SDM","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Chen et al., 2016] Chao Chen, Dongsheng Li, Qin Lv, Junchi Yan, Stephen M Chu, and Li Shang. Mpma: mix- ture probabilistic matrix approximation for collaborative filtering. In IJCAI, pages 1382-1388, 2016.","title":"Mpma: mixture probabilistic matrix approximation for collaborative filtering","authors":"Chao Chen, Dongsheng Li, Qin Lv, Junchi Yan, Stephen M Chu, Li Shang","year":"2016","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2016/199"},{"position":4,"raw":"[Devooght et al., 2015] Robin Devooght, Nicolas Kourtellis, and Amin Mantrach. Dynamic matrix factorization with priors on unknown values. In SIGKDD, pages 189-198. ACM, 2015.","title":"Dynamic matrix factorization with priors on unknown values","authors":"Devooght","year":"2015","venue":"SIGKDD","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Eckart and Young, 1936] Carl Eckart and Gale Young. The approximation of one matrix by another of lower rank. Psychometrika, 1(3):211-218, 1936.","title":"The approximation of one matrix by another of lower rank","authors":"Young ; Eckart, Carl Eckart, Gale Young","year":"1936","venue":"Psychometrika","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Halko et al., 2011] Nathan Halko, Per-Gunnar Martinsson, and Joel A Tropp. Finding structure with randomness: Probabilistic algorithms for constructing approximate ma- trix decompositions. SIAM review, 53(2):217-288, 2011.","title":"Finding structure with randomness: Probabilistic algorithms for constructing approximate matrix decompositions","authors":"Halko","year":"2011","venue":"SIAM review","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Hatemi-J, 2004] Abdulnasser Hatemi-J. Multivariate tests for autocorrelation in the stable and unstable var models. Economic Modelling, 21(4):661-683, 2004.","title":"Abdulnasser Hatemi-J. Multivariate tests for autocorrelation in the stable and unstable var models","authors":"-J Hatemi","year":"2004","venue":"Economic Modelling","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Hazan, 2008] Elad Hazan. Sparse approximate solutions to semidefinite programs. In Latin American Symposium on Theoretical Informatics, pages 306-316. Springer, 2008.","title":"Sparse approximate solutions to semidefinite programs","authors":"Elad Hazan","year":"2008","venue":"Latin American Symposium on Theoretical Informatics","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Lee and Seung, 1999] Daniel D Lee and H Sebastian Seung. Learning the parts of objects by non-negative matrix fac- torization. Nature, 401(6755):788-791, 1999.","title":"Learning the parts of objects by non-negative matrix factorization","authors":"D Daniel, H Lee, Seung Sebastian","year":"1999","venue":"Nature","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Liberty, 2013] Edo Liberty. Simple and deterministic matrix sketching. In SIGKDD, pages 581-588. ACM, 2013.","title":"Edo Liberty. Simple and deterministic matrix sketching","authors":"Liberty","year":"2013","venue":"SIGKDD","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Lin et al., 2017] Hao Lin, Hengshu Zhu, Yuan Zuo, Chen Zhu, Junjie Wu, and Hui Xiong. Collaborative company profiling: insights from an employees perspective. AAAI, 2017.","title":"Collaborative company profiling: insights from an employees perspective","authors":"Hengshu Hao Lin, Yuan Zhu, Chen Zuo, Junjie Zhu, Hui Wu, Xiong","year":"2017","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Liu et al., 2011] Qi Liu, Yong Ge, Zhongmou Li, Enhong Chen, and Hui Xiong. Personalized travel package rec- ommendation. In Data Mining (ICDM), 2011 IEEE 11th International Conference on, pages 407-416. IEEE, 2011.","title":"Personalized travel package recommendation","authors":"Qi Liu, Yong Ge, Zhongmou Li, Enhong Chen, Hui Xiong","year":"2011","venue":"IEEE 11th International Conference on","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Luo et al., 2012] Xin Luo, Yunni Xia, and Qingsheng Zhu. Incremental collaborative filtering recommender based on regularized matrix factorization. Knowledge-Based Sys- tems, 27:271-280, 2012.","title":"Incremental collaborative filtering recommender based on regularized matrix factorization","authors":"Xin Luo, Yunni Xia, Qingsheng Zhu","year":"2012","venue":"Knowledge-Based Systems","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Matuszyk et al., 2015] Pawel Matuszyk, João Vinagre, Myra Spiliopoulou, Alípio Mário Jorge, and João Gama. Forgetting methods for incremental matrix factorization in recommender systems. In Proceedings of the 30th Annual ACM Symposium on Applied Computing, pages 947-953. ACM, 2015.","title":"Forgetting methods for incremental matrix factorization in recommender systems","authors":"Pawel Matuszyk, João Vinagre, Myra Spiliopoulou, Alípio Mário, Jorge, João Gama","year":"2015","venue":"Proceedings of the 30th Annual ACM Symposium on Applied Computing","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Rendle and Schmidt-Thieme, 2008] Steffen Rendle and Lars Schmidt-Thieme. Online-updating regularized kernel matrix factorization models for large-scale recommender systems. In RecSys, pages 251-258. ACM, 2008.","title":"Online-updating regularized kernel matrix factorization models for large-scale recommender systems","authors":"Steffen Rendle, Lars Schmidt-Thieme","year":"2008","venue":"RecSys","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Salakhutdinov and Mnih, 2008] Ruslan Salakhutdinov and Andriy Mnih. Bayesian probabilistic matrix factorization using markov chain monte carlo. In ICML, pages 880-887. ACM, 2008.","title":"Ruslan Salakhutdinov and Andriy Mnih. Bayesian probabilistic matrix factorization using markov chain monte carlo","authors":"Mnih Salakhutdinov","year":"2008","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Sarwar et al., 2002] Badrul Sarwar, George Karypis, Joseph Konstan, and John Riedl. Incremental singular value de- composition algorithms for highly scalable recommender systems. In Fifth International Conference on Computer and Information Science, pages 27-28. Citeseer, 2002.","title":"Incremental singular value decomposition algorithms for highly scalable recommender systems","authors":"Badrul Sarwar, George Karypis, Joseph Konstan, John Riedl","year":"2002","venue":"Fifth International Conference on Computer and Information Science","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Scott Hacker and Hatemi-J, 2008] R Scott Hacker and Ab- dulnasser Hatemi-J. Optimal lag-length choice in stable and unstable var models under situations of homoscedas- ticity and arch. Journal of Applied Statistics, 35(6):601- 615, 2008.","title":"R Scott Hacker and Abdulnasser Hatemi-J. Optimal lag-length choice in stable and unstable var models under situations of homoscedasticity and arch","authors":"Scott Hacker, Hatemi-J","year":"2008","venue":"Journal of Applied Statistics","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Song et al., 2015] Qiang Song, Jian Cheng, and Hanqing Lu. Incremental matrix factorization via feature space re- learning for recommender system. In RecSys, pages 277- 280. ACM, 2015.","title":"Incremental matrix factorization via feature space relearning for recommender system","authors":"Qiang Song, Jian Cheng, Hanqing Lu","year":"2015","venue":"RecSys","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Vinagre et al., 2014] João Vinagre, Alípio Mário Jorge, and João Gama. Fast incremental matrix factorization for rec- ommendation with positive-only feedback. In Internation- al Conference on User Modeling, Adaptation, and Person- alization, pages 459-470. Springer, 2014.","title":"Fast incremental matrix factorization for recommendation with positive-only feedback","authors":"João Vinagre, Alípio Mário, Jorge, João Gama","year":"2014","venue":"International Conference on User Modeling, Adaptation, and Personalization","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Wang et al., 2011] Fei Wang, Hanghang Tong, and Ching- Yung Lin. Towards evolutionary nonnegative matrix fac- torization. In AAAI, volume 11, pages 501-506, 2011.","title":"Towards evolutionary nonnegative matrix factorization","authors":"Fei Wang, Hanghang Tong, Ching-Yung Lin","year":"2011","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Wu et al., 2012] Le Wu, Enhong Chen, Qi Liu, Linli X- u, Tengfei Bao, and Lei Zhang. Leveraging tagging for neighborhood-aware probabilistic matrix factorization. In CIKM, pages 1854-1858. ACM, 2012.","title":"Leveraging tagging for neighborhood-aware probabilistic matrix factorization","authors":"Le Wu, Enhong Chen, Qi Liu, Linli Xu, Tengfei Bao, Lei Zhang","year":"2012","venue":"CIKM","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Wu et al., 2017] Le Wu, Yong Ge, Qi Liu, Enhong Chen, Richang Hong, Junping Du, and Meng Wang. Modeling the evolution of users preferences and social links in social networking services. IEEE Transactions on Knowledge and Data Engineering, 29(6):1240-1253, 2017.","title":"Modeling the evolution of users preferences and social links in social networking services","authors":"Le Wu, Yong Ge, Qi Liu, Enhong Chen, Richang Hong, Junping Du, Meng Wang","year":"2017","venue":"IEEE Transactions on Knowledge and Data Engineering","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Zeng et al., 2015] Guangxiang Zeng, Hengshu Zhu, Qi Liu, Ping Luo, Enhong Chen, and Tong Zhang. Matrix factor- ization with scale-invariant parameters. In IJCAI, pages 4017-4024. AAAI Press, 2015.","title":"Matrix factorization with scale-invariant parameters","authors":"Guangxiang Zeng, Hengshu Zhu, Qi Liu, Ping Luo, Enhong Chen, Tong Zhang","year":"2015","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2015/564"},{"position":25,"raw":"[Zhu et al., 2015] Hengshu Zhu, Enhong Chen, Hui Xiong, Kuifei Yu, Huanhuan Cao, and Jilei Tian. Mining mo- bile user preferences for personalized context-aware rec- ommendation. ACM Transactions on Intelligent Systems and Technology (TIST), 5(4):58, 2015.","title":"Mining mobile user preferences for personalized context-aware recommendation","authors":"Zhu","year":"2015","venue":"ACM Transactions on Intelligent Systems and Technology (TIST)","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}