ABSTRACT
Recommender systems powering online multi-stakeholder platforms often face the challenge of jointly optimizing multiple objectives, in an attempt to efficiently match suppliers and consumers. Examples of such objectives include user behavioral metrics (e.g. clicks, streams, dwell time, etc), supplier exposure objectives (e.g. diversity) and platform centric objectives (e.g. promotions). Jointly optimizing multiple metrics in online recommender systems remains a challenging task. Recent work has demonstrated the prowess of contextual bandits in powering recommendation systems to serve recommendation of interest to users. This paper aims at extending contextual bandits to multi-objective setting so as to power recommendations in a multi-stakeholder platforms.
Specifically, in a contextual bandit setting, we learn a recommendation policy that can optimize multiple objectives simultaneously in a fair way. This multi-objective online optimization problem is formalized by using the Generalized Gini index (GGI) aggregation function, which combines and balances multiple objectives together. We propose an online gradient ascent learning algorithm to maximise the long-term vectorial rewards for different objectives scalarised using the GGI function. Through extensive experiments on simulated data and large scale music recommendation data from Spotify, a streaming platform, we show that the proposed algorithm learns a superior policy among the disparate objectives compared with other state-of-the-art approaches.
- Gediminas Adomavicius and YoungOk Kwon. 2007. New Recommendation Techniques for Multicriteria Rating Systems. IEEE Intelligent Systems (2007).Google ScholarDigital Library
- Deepak Agarwal, Bee-Chung, Pradheep, and Xuanhui. 2011. Click shaping to optimize multiple objectives. In Proceedings of KDD 2011.Google ScholarDigital Library
- Deepak Agarwal, Bee-Chung Chen, Pradheep Elango, and Xuanhui Wang. 2012. Personalized click shaping through lagrangian duality for online recommendation. In Proceedings of SIGIR 2012.Google ScholarDigital Library
- Leon Barrett and Srini Narayanan. 2008. Learning All Optimal Policies with Multiple Criteria. In ICML. 41--47.Google Scholar
- Róbert Busa-Fekete, Balázs Szörényi, Paul Weng, and Shie Mannor. 2017. Multi-objective Bandits: Optimizing the Generalized Gini Index. In ICML.Google Scholar
- Konstantina Christakopoulou, Jaya Kawale, and Arindam Banerjee. Recommendation with capacity constraints. In Proceedings of CIKM 2017.Google ScholarDigital Library
- Wei Chu and Seung-Taek Park. 2009. Personalized Recommendation on Dynamic Content Using Predictive Bilinear Models. In WWW.Google Scholar
- Paolo Cremonesi, Yehuda Koren, and Roberto Turrin. 2010. Performance of Recommender Algorithms on Top-n Recommendation Tasks. In RecSys.Google Scholar
- M. M. Drugan and A. Nowe. 2013. Designing multi-objective multi-armed bandits algorithms: A study. In International Joint Conference on Neural Networks (IJCNN).Google Scholar
- Zoltán Gábor, Zsolt Kalmár, and Csaba Szepesvári. 1998. Multi-criteria Reinforcement Learning. In ICML. 197--205.Google Scholar
- Rupesh Gupta, Guanfeng Liang, Ravi Kiran Tseng, Xiaoyu Chen, and Romer Rosales. Email volume optimization at LinkedIn. In KDD 2016.Google ScholarDigital Library
- Tamas Jambor and Jun Wang. Optimizing multiple objectives in collaborative filtering. In Proceedings of RecSys 2010.Google ScholarDigital Library
- Dietmar Jannach and Malte Ludewig. 2017. When recurrent neural networks meet the neighborhood for session-based recommendation. In Proceedings of the Eleventh ACM Conference on Recommender Systems. ACM, 306--310.Google ScholarDigital Library
- Thorsten Joachims. 2002. Optimizing search engines using clickthrough data. Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining. ACM, 133--142.Google ScholarDigital Library
- I. Y. Kim and O. L. de Weck. 2006. Adaptive weighted sum method for multiobjective optimization: a new method for Pareto front generation. Structural and Multidisciplinary Optimization, Vol. 31, 2 (2006), 105--116.Google ScholarCross Ref
- Anisio Lacerda. 2015. Contextual Bandits for Multi-objective Recommender Systems. In Proceedings of the 2015 Brazilian Conference on Intelligent Systems (BRACIS). 68--73.Google ScholarDigital Library
- Kleanthi Lakiotaki, Nikolaos F Matsatsinis, and Alexis Tsoukias. 2011. Multicriteria user modeling in recommender systems. IEEE Intelligent Systems (2011).Google ScholarDigital Library
- John Langford and Tong Zhang. 2008. The Epoch-Greedy Algorithm for Multi-armed Bandits with Side Information. NIPS.Google Scholar
- Lihong Li, Wei Chu, John Langford, and Robert E. Schapire. 2010. A Contextual-bandit Approach to Personalized News Article Recommendation. In WWW.Google Scholar
- Lihong Li, Wei Chu, John Langford, and Xuanhui Wang. 2011. Unbiased Offline Evaluation of Contextual-bandit-based News Article Recommendation Algorithms. In WSDM.Google Scholar
- C. Liu, X. Xu, and D. Hu. 2015. Multiobjective Reinforcement Learning: A Comprehensive Overview. IEEE Transactions on Systems, Man, and Cybernetics (2015).Google Scholar
- Donald W. Marquardt and Ronald D. Snee. 1975. Ridge Regression in Practice. The American Statistician, Vol. 29, 1 (1975), 3--20.Google Scholar
- James McInerney, Benjamin Lacker, Samantha Hansen, Karl Higley, Hugues Bouchard, Alois Gruson, and Rishabh Mehrotra. Explore, Exploit, and Explain: Personalizing Explainable Recommendations with Bandits. In Proceedings of RecSys 2018.Google Scholar
- Rishabh Mehrotra and Benjamin Carterette. 2019. Recommendations in a marketplace. In Proceedings of the 13th ACM Conference on Recommender Systems. 580--581.Google ScholarDigital Library
- Rishabh Mehrotra, James McInerney, Hugues Bouchard, Mounia Lalmas, and Fernando Diaz. 2018. Towards a Fair Marketplace: Counterfactual Evaluation of the trade-off between Relevance, Fairness & Satisfaction in Recommendation Systems. In CIKM.Google Scholar
- K. Van Moffaert, K. Van Vaerenbergh, P. Vrancx, and A. Nowe.Google Scholar
- Eric Moulines and Francis R. Bach. 2011. Non-Asymptotic Analysis of Stochastic Approximation Algorithms for Machine Learning. NIPS.Google Scholar
- Wodzimierz Ogryczak and Tomasz Sliwinski. 2003. On solving linear programs with the ordered weighted averaging objective. European Journal of Operational Research, Vol. 148, 1 (2003), 80--91.Google ScholarCross Ref
- Saba Q. Yahyaa, Madalina M. Drugan, and Bernard Manderick. 2014. Knowledge Gradient for Multi-objective Multi-armed Bandit Algorithms. In Proceedings of the 6th International Conference on Agents and Artificial Intelligence - Volume 1.Google Scholar
- Marco Tulio Ribeiro, Lacerda, Veloso, and Ziviani. Pareto-efficient hybridization for multi-objective recommender systems. In RecSys 2012.Google ScholarDigital Library
- Herbert Robbins and Sutton Monro. 1951. A stochastic approximation method. The Annals of Mathematical Statistics, Vol. 22, 3 (1951), 400--407.Google ScholarCross Ref
- Lili Shan, Lei Lin, and Chengjie Sun. Combined Regression and Tripletwise Learning for Conversion Rate Prediction in Real-Time Bidding Advertising. In SIGIR 2018.Google Scholar
- Aleksandrs Slivkins. 2014. Contextual Bandits with Similarity Information. J. Mach. Learn. Res., Vol. 15, 1 (2014), 2533--2568.Google ScholarDigital Library
- Richard S. Sutton and Francis Bach. 1998. Reinforcement Learning: An Introduction. MIT Press.Google Scholar
- Krysta M Svore, Maksims N Volkovs, and Christopher JC Burges. Learning to rank with multiple objective functions. In Proceedings of WWW 2011.Google ScholarDigital Library
- Cem Tekin and Eralp Turug ay. 2018. Multi-objective contextual multi-armed bandit with a dominant objective. IEEE Transactions on Signal Processing (2018).Google ScholarDigital Library
- Eralp Turug ay, Doruk Öner, and Cem Tekin. 2018. Multi-objective contextual bandit problem with similarity information. arXiv preprint arXiv:1803.04015 (2018).Google Scholar
- Umair ul Hassan and Edward Curry. 2016. Efficient task assignment for spatial crowdsourcing: A combinatorial fractional optimization approach with semi-bandit learning. Expert Systems with Applications, Vol. 58 (2016), 36--56.Google ScholarDigital Library
- John A. Weymark. 1981. Generalized Gini inequality indices. Mathematical Social Sciences, Vol. 1 (1981), 409--430.Google ScholarCross Ref
- Lin Xiao, Minand, Zhaoquan, L Yiqun, and Ma Shaoping. Fairness-aware group recommendation with pareto-efficiency. In RecSys 2018.Google Scholar
- R. R. Yager. On ordered weighted averaging aggregation operators in multicriteria decisionmaking. IEEE Transactions on Systems, Man, & Cybernetics ( ????).Google Scholar
- Saba Yahyaa, Madalina Drugan, and Bernard Manderick. 2015. Thompson Sampling in the Adaptive Linear Scalarized Multi Objective Multi Armed Bandit. In Proceedings of the 7th International Conference on Agents and Artificial Intelligence.Google ScholarDigital Library
- Xing Yi, Liangjie Hong, Erheng Zhong, Nanthan Nan Liu, and Suju Rajan. Beyond clicks: dwell time for personalization. In Proceedings of RecSys 2014.Google ScholarDigital Library
- Chongjie Zhang and Julie A Shah. 2014. Fairness in Multi-Agent Sequential Decision-Making. NIPS. 2636--2644.Google Scholar
Index Terms
- Bandit based Optimization of Multiple Objectives on a Music Streaming Platform
Recommendations
Handling multiple objectives with biogeography-based optimization
Biogeography-based optimization (BBO) is a new evolutionary optimization method inspired by biogeography. In this paper, BBO is extended to a multi-objective optimization, and a biogeography-based multi-objective optimization (BBMO) is introduced, which ...
Music recommendations for groups of users
ImmersiveMe '13: Proceedings of the 2013 ACM international workshop on Immersive media experiencesThis paper presents an algorithm capable of providing meaningful recommendations to small sets of users. We consider not only rating patterns, bias tendencies, and temporal fluctuations, but also group-leaders. The approach here presented intends to ...
Optimizing multiple objectives in collaborative filtering
RecSys '10: Proceedings of the fourth ACM conference on Recommender systemsThis paper is about the utility of making personalized recommendations. While it is important to accurately predict the target user's preference, in practice the accuracy should not be the only concern; a useful recommender system needs to consider the ...
Comments