ABSTRACT
Recommending personalized content to users is a long-standing challenge to many online services including Facebook, Yahoo, Linkedin and Twitter. Traditional recommendation models such as latent factor models and feature-based models are usually trained for all users and optimize an "average" experience for them, yielding sub-optimal solutions. Although multi-task learning provides an opportunity to learn personalized models per user, learning algorithms are usually tailored to specific models (e.g., generalized linear model, matrix factorization and etc.), creating obstacles for a unified engineering interface, which is important for large Internet companies. In this paper, we present an empirical framework to learn user-specific personal models for content recommendation by utilizing gradient information from a global model. Our proposed method can potentially benefit any model that can be optimized through gradients, offering a lightweight yet generic alternative to conventional multi-task learning algorithms for user personalization. We demonstrate the effectiveness of the proposed framework by incorporating it in three popular machine learning algorithms including logistic regression, gradient boosting decision tree and matrix factorization. Our extensive empirical evaluation shows that the proposed framework can significantly improve the efficiency of personalized recommendation in real-world datasets.
- Deepak Agarwal and Bee-Chung Chen. Regression-based Latent Factor Models. In Proceedings of KDD 2009. 19--28. Google ScholarDigital Library
- Deepak Agarwal, Bo Long, Jonathan Traupman, Doris Xin, and Liang Zhang. LASER: A Scalable Response Prediction Platform for Online Advertising. In Proceedings of WSDM 2014. 173--182. Google ScholarDigital Library
- Xavier Amatriain and Deepak Agarwal. 2016. Tutorial: Lessons Learned from Building Real-life Recommender Systems. In Proceedings of the 10th ACM Conference on Recommender Systems (RecSys '16). ACM, New York, NY, USA, 433--433. Google ScholarDigital Library
- Xavier Amatriain, Neal Lathia, Josep M. Pujol, Haewoon Kwak, and Nuria Oliver. 2009. The Wisdom of the Few: A Collaborative Filtering Approach Based on Expert Opinions from the Web. In Proceedings of the 32Nd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR '09). ACM, New York, NY, USA, 532--539. Google ScholarDigital Library
- Yoshua Bengio, Jérôme Louradour, Ronan Collobert, and Jason Weston. 2009. Curriculum Learning. In Proceedings of the 26th Annual International Conference on Machine Learning (ICML '09). ACM, New York, NY, USA, 41--48. Google ScholarDigital Library
- J. Bennett and S. Lanning. 2007. The Netflix Prize. In Proceedings of the KDD Cup Workshop 2007. 3--6.Google Scholar
- Alex Beutel, Ed H. Chi, Zhiyuan Cheng, Hubert Pham, and John Anderson. 2017. Beyond Globally Optimal: Focused Learning for Improved Recommendations. In Proceedings of the 26th International Conference on World Wide Web (WWW '17). Google ScholarDigital Library
- Christopher J. C. Burges. 2010. From RankNet to LambdaRank to LambdaMART: An Overview. Technical Report. Microsoft Research. http://research.microsft.com/en-us/um/people/cburges/tech reports/MSR-TR-2010-82.pdfGoogle Scholar
- Allison J. B. Chaney, David M. Blei, and Tina Eliassi-Rad. 2015. A Probabilistic Model for Using Social Networks in Personalized Item Recommendation. In Proceedings of the 9th ACM Conference on Recommender Systems (RecSys '15). ACM, New York, NY, USA, 43--50. Google ScholarDigital Library
- Olivier Chapelle, Pannagadatta Shivaswamy, Srinivas Vadrevu, Kilian Weinberger, Ya Zhang, and Belle Tseng. 2011. Boosted multi-task learning. Machine Learning 85, 1 (2011), 149--173. Google ScholarDigital Library
- Tianqi Chen and Carlos Guestrin. XGBoost: A Scalable Tree Boosting System. In Proceedings of KDD 2016. 785--794. Google ScholarDigital Library
- David R. Cox. 1958. The regression analysis of binary sequences (with discussion). J. Roy Stat Soc B. 20 (1958), 215--242.Google ScholarCross Ref
- Jerome H. Friedman. 2000. Greedy Function Approximation: A Gradient Boosting Machine. Annals of Statistics 29 (2000), 1189--1232.Google ScholarCross Ref
- Jerome H. Friedman. 2002. Stochastic gradient boosting. Computational Statistics & Data Analysis 38, 4 (2002), 367--378. Nonlinear Methods and Data Mining. Google ScholarDigital Library
- Simon Funk. 2006. Netflix Update: Try this at Home. (2006).Google Scholar
- Bikash Joshi, Franck Iutzeler, and Massih-Reza Amini. 2016. Asynchronous Distributed Matrix Factorization with Similar User and Item Based Regularization. In Proceedings of the 10th ACM Conference on Recommender Systems (RecSys '16). ACM, New York, NY, USA, 75--78. Google ScholarDigital Library
- Alexandros Karatzoglou, Linas Baltrunas, and Yue Shi. 2013. Learning to Rank for Recommender Systems. In Proceedings of the 7th ACM Conference on Recommender Systems (RecSys '13). ACM, New York, NY, USA, 493--494. Google ScholarDigital Library
- Gunhee Kim and Eric P. Xing. Time-sensitive Web Image Ranking and Retrieval via Dynamic Multi-task Regression. In Proceedings of WSDM 2013. 163--172. Google ScholarDigital Library
- Yehuda Koren. Factorization Meets the Neighborhood: A Multifaceted Collaborative Filtering Model. In Proceedings of KDD 2008. 426--434. Google ScholarDigital Library
- Roy Levin, Hassan Abassi, and Uzi Cohen. 2016. Guided Walk: A Scalable Recommendation Algorithm for Complex Heterogeneous Social Networks. In Proceedings of the 10th ACM Conference on Recommender Systems (RecSys '16). ACM, New York, NY, USA, 293--300. Google ScholarDigital Library
- Ping Li. Robust LogitBoost and Adaptive Base Class (ABC) LogitBoost. In Proceedings of the Twenty-Sixth Conference on Uncertainty in Artificial Intelligence (UAI2010). 302--311. https://dslpitt.org/uai/displayArticleDetails.jsp?mmnu=1&smnu=2&article_id=2158&proceeding_id=26 Google ScholarDigital Library
- Peter Lofgren, Siddhartha Banerjee, and Ashish Goel. 2016. Personalized PageRank Estimation and Search: A Bidirectional Approach. In Proceedings of the Ninth ACM International Conference on Web Search and Data Mining (WSDM '16). ACM, New York, NY, USA, 163--172. Google ScholarDigital Library
- H. Brendan McMahan. 2011. Follow-the-Regularized-Leader and Mirror Descent: Equivalence Theorems and L1 Regularization. In Proceedings of the 14th International Conference on Artificial Intelligence and Statistics (AISTATS).Google Scholar
- H. Brendan McMahan, Gary Holt, D. Sculley, Michael Young, Dietmar Ebner, Julian Grady, Lan Nie, Todd Phillips, Eugene Davydov, Daniel Golovin, Sharat Chikkerur, Dan Liu, Martin Wattenberg, Arnar Mar Hrafnkelsson, Tom Boulos, and Jeremy Kubica. Ad Click Prediction: a View from the Trenches. In Proceedings of KDD 2013. 1222--1230. Google ScholarDigital Library
- Xu Miao, Chun-Te Chu, Lijun Tang, Yitong Zhou, Joel Young, and Anmol Bhasin. Distributed Personalization. In Proceedings of KDD 2015. 1989--1998. Google ScholarDigital Library
- Xia Ning and George Karypis. 2010. Multi-task learning for recommender systems. Journal of Machine Learning Research 13 (2010), 269--284.Google Scholar
- Alexandre Passos, Piyush Rai, Jacques Wainer, and Hal Daumé III. Flexible Modeling of Latent Task Structures in Multitask Learning. In Proceedings of ICML 2012. 1103--1110. Google ScholarDigital Library
- Steffen Rendle. 2012. Factorization Machines with libFM. ACM Trans. Intell. Syst. Technol. 3, 3, Article 57 (May 2012), 22 pages. Google ScholarDigital Library
- Steffen Rendle, Christoph Freudenthaler, Zeno Gantner, and Lars Schmidt-Thieme. 2009. BPR: Bayesian Personalized Ranking from Implicit Feedback. In Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence (UAI '09). AUAI Press, Arlington, Virginia, United States, 452--461. http://dl.acm.org/citation.cfm?id=1795114.1795167 Google ScholarDigital Library
- Dhaval Shah, Pramod Koneru, Parth Shah, and Rohit Parimi. 2016. News Recommendations at Scale at Bloomberg Media: Challenges and Approaches. In Proceedings of the 10th ACM Conference on Recommender Systems (RecSys '16). ACM, New York, NY, USA, 369--369. Google ScholarDigital Library
- S. H. Walker and D. B. Duncan. 1967. Estimation of the probability of an event as a function of several independent variables. Biometrika 54, 1 (June 1967), 167--179. http://view.ncbi.nlm.nih.gov/pubmed/6049533Google ScholarCross Ref
- Hongning Wang, Xiaodong He, Ming-Wei Chang, Yang Song, Ryen W. White, and Wei Chu. Personalized Ranking Model Adaptation for Web Search. In Proceedings of SIGIR 2013. 323--332. Google ScholarDigital Library
- Kilian Weinberger, Anirban Dasgupta, John Langford, Alex Smola, and Josh Attenberg. Feature Hashing for Large Scale Multitask Learning. In Proceedings of ICML 2009. 1113--1120. Google ScholarDigital Library
- XianXing Zhang, Yitong Zhou, Yiming Ma, Bee-Chung Chen, Liang Zhang, and Deepak Agarwal. GLMix: Generalized Linear Mixed Models For LargeScale Response Prediction. In Proceedings of KDD 2016. 363--372. Google ScholarDigital Library
- Zhaohui Zheng, Hongyuan Zha, Tong Zhang, Olivier Chapelle, Keke Chen, and Gordon Sun. A General Boosting Method and its Application to Learning Ranking Functions for Web Search. In Proceedings of NIPS 2008. 1697--1704. Google ScholarDigital Library
Index Terms
- A Gradient-based Adaptive Learning Framework for Efficient Personal Recommendation
Recommendations
Personalized recommendation based on the personal innovator degree
RecSys '09: Proceedings of the third ACM conference on Recommender systemsThis paper proposes a novel Collaborative Filtering scheme; it focuses on the dynamics and precedence of user preference to recommend items that match the latest preference of the target user. In predicting which items this user will purchase in the ...
Personalized Content Recommendation and User Satisfaction: Theoretical Synthesis and Empirical Findings
Personalized services are increasingly popular in the Internet world. This study identifies theories related to the use of personalized content services and their effect on user satisfaction. Three major theories have been identified-information ...
New Recommendation Techniques for Multicriteria Rating Systems
Traditional single-rating recommender systems have been successful in a number of personalization applications, but the research area of multicriteria recommender systems has been largely untouched. Taking full advantage of multicriteria ratings in ...
Comments