journal article
Nov 27, 2024
Mitigating Exposure Bias in Recommender Systems—A Comparative Analysis of Discrete Choice Models
ACM Transactions on Recommender Systems
Vol. 3
No. 2
pp. 1-37
·
Association for Computing Machinery (ACM)
Abstract
When implicit feedback recommender systems expose users to items, they influence the users’ choices and, consequently, their own future recommendations. This effect is known as exposure bias, and it can cause undesired effects such as filter bubbles and echo chambers. Previous research has used multinomial logit models to reduce exposure bias through over-exposure on synthesized data. We hypothesized that these findings hold true for human choice data to a limited degree and that advanced discrete choice models further reduced bias. We also investigated whether the composition of choice sets can cause exposure bias. In pursuing our research questions, we collected partially biased human choices in a controlled online user study. In two experiments, we evaluated how discrete choice–based recommender systems and baselines react to over-exposure and to over- and under-competitive choice sets. Our results confirmed that leveraging choice set information mitigates exposure bias. The multinomial logit model reduced exposure bias, comparably with the other discrete choice models. Choice set competitiveness biased the models that did not consider choice alternatives. Our findings suggest that discrete choice models are highly effective at mitigating exposure bias in recommender systems and that existing recommender systems may suffer more exposure bias than previously thought.
Topics
No keywords indexed for this article. Browse by subject →
References
107
[1]
Jiawei Chen Hande Dong Xiang Wang Fuli Feng Meng Wang and Xiangnan He. 2023. Bias and debias in recommender system: A survey and future directions. ACM Trans. Inf. Syst. 41 3 Article 67 (July 2023) 39 pages.
10.1145/3564284
[2]
Yuta Saito, Suguru Yaginuma, Yuta Nishino, Hayato Sakata, and Kazuhide Nakata. 2020. Unbiased recommender learning from missing-not-at-random implicit feedback. In Proceedings of the 13th International Conference on Web Search and Data Mining.
[3]
Jessa Bekker Pieter Robberechts and Jesse Davis. 2019. Beyond the selected completely at random assumption for learning from positive and unlabeled data. In Proceedings Joint European Conference on Machine Learning and Knowledge Discovery in Databases.
10.1007/978-3-030-46147-8_5
[4]
Dietmar Jannach, Lukas Lerche, and Markus Zanker. 2018. Recommending Based on Implicit Feedback: Social Information Access. Springer International, Cham, 510–569.
10.1007/978-3-319-90092-6_14
[5]
H. Abdollahpouri and M. Mansoury. 2020. Multi-sided Exposure Bias in Recommendation. In Proceedings of the ACM KDD Workshop on Industrial Recommendation Systems.
[6]
Masoud Mansoury, Himan Abdollahpouri, Mykola Pechenizkiy, Bamshad Mobasher, and Robin Burke. 2020. Feedback loop and bias amplification in recommender systems. In Proceedings of the 29th ACM International Conference on Information and Knowledge Management.
[7]
Ray Jiang, Silvia Chiappa, Tor Lattimore, Andras György, and Pushmeet KohliJiang. 2019. Degenerate feedback loops in recommender systems. In Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society.
[8]
Yingqiang Ge, Shuya Zhao, Honglu Zhou, Changhua Pei, Fei Sun, Wenwu Ou, and Yongfeng Zhang. 2020. Understanding echo chambers in E-commerce recommender systems. In Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval.
[9]
Eli Pariser. 2012. The Filter Bubble: How the New Personalized Web Is Changing What We Read and How We Think. Penguin.
10.3139/9783446431164
[10]
Seth Flaxman, Sharad Goel, and Justin M. Rao. 2013. Ideological segregation and the effects of social media on news consumption. SSRN Electr. J. (2013).
10.2139/ssrn.2363701
[11]
Tianxin Wei, Fuli Feng, Jiawei Chen, Chufeng Shi, Ziwei Wu, Jinfeng Yi, and Xiangnan He. 2021. Model-Agnostic counterfactual reasoning for eliminating popularity bias in recommender system. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining.
[12]
Michael D. Ekstrand, Robin Burke, and Fernando Diaz. 2019. Fairness and discrimination in recommendation and retrieval. In Proceedings of the 13th ACM Conference on Recommender Systems.
[13]
Himan Abdollahpouri, Masoud Mansoury, Robin Burke, and Bamshad Mobasher. 2020. The connection between popularity bias, calibration, and fairness in recommendation. In Proceedings of the 14th ACM Conference on Recommender Systems.
[14]
Hongzhi Yin Yizhou Sun Guandong Xu and Evangelos Kanoulas. 2023. Trustworthy recommendation and search: Introduction to the special Issue - Part 1. ACM Trans. Inf. Syst. 41 3 Article 51 (July 2023) 5 pages.
10.1145/3579995
[15]
Rong Pan, Yunhong Zhou, Bin Cao, Nathan N. Liu, Rajan Lukose, Martin Scholz, and Qiang Yang. 2008. One-Class collaborative filtering. In Proceedings of the 8th IEEE International Conference on Data Mining.
[16]
Rong Pan and Martin Scholz. 2009. Mind the gaps. In Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.
[17]
Dawen Liang, Laurent Charlin, James McInerney, and David M. Blei. 2016. Modeling User Exposure in Recommendation. In Proceedings of the 25th International Conference on World Wide Web.
[18]
Jingtao Ding, Yuhan Quan, Xiangnan He, Yong Li, and Depeng Jin. 2019. Reinforced negative sampling for recommendation with exposure data. In Proceedings of the 28th International Joint Conference on Artificial Intelligence.
[19]
Diego Carraro and Derek Bridge. 2020. Debiased offline evaluation of recommender systems. In Proceedings of the 35th Annual ACM Symposium on Applied Computing.
[20]
Chang Zhou, Jianxin Ma, Jianwei Zhang, Jingren Zhou, and Hongxia Yang. 2021. Contrastive learning for debiased candidate generation in large-scale recommender systems. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining.
10.1145/3447548
[21]
Thorsten Krause, Daniel Stattkus, Alina Deriyeva, Jan H. Beinke, and Oliver Thomas. 2022. Beyond the rating matrix: Debiasing implicit feedback loops in collaborative filtering. In Proceedings International Conference on Wirtschaftsinformatik.
[22]
Gökhan Çapan, Ilker Gündoğdu, Ali Caner Türkmen, and Ali Taylan Cemgil. 2022. Dirichlet–Luce choice model for learning from interactions. User Model. User-Adapt. Interact. 32 (June 2022), 611–648.
10.1007/s11257-022-09331-0
[23]
Gökhan Çapan Ilker Gündoğdu Ali Caner Türkmen Çağrı Sofuoğlu and Ali Taylan Cemgil. 2019. A Bayesian choice model for eliminating feedback loops. arXiv:1908.05640. Retrieved from https://arxiv.org/abs/1908.05640
[24]
Yu Zheng, Chen Gao, Xiang Li, Xiangnan He, Yong Li, and Depeng Jin. 2021. Disentangling user interest and conformity for recommendation with causal embedding. In Proceedings of the Web Conference.
[25]
Qi Wan, Xiangnan He, Xiang Wang, Jiancan Wu, and Wei Guo, Ruiming Tang. 2022. Cross pairwise ranking for unbiased item recommendation. In Proceedings of the ACM Web Conference.
[26]
Yuta Saito. 2020. Unbiased pairwise learning from biased implicit feedback. In Proceedings of the ACM SIGIR on International Conference on Theory of Information Retrieval.
[27]
Aydin Alptekinoglu and John H. Semple. 2013. The exponomial choice model. SSRN Electr. J. (2013)
10.2139/ssrn.2210478
[28]
Kenneth E. Train. 2009. Discrete Choice Methods with Simulation (2nd. ed.). Cambridge University Press, Cambridge, UK.
[29]
Sami Khenissi, Mariem. Boujelbene, and Olfa Nasraoui. 2020. Theoretical modeling of the iterative properties of user discovery in a collaborative filtering recommender system. In Proceedings of the 14th ACM Conference on Recommender Systems.
[30]
Qijie Shen, Wanjie Tao, Jing Zhang, Hong Wen, Zulong Chen, and Quan Lu. 2021. SAR-Net. In Proceedings of the 30th ACM International Conference on Information and Knowledge Management.
[31]
Nikzad Chizari Niloufar Shoeibi and María N. Moreno-García. 2022. A comparative analysis of bias amplification in graph neural network approaches for recommender systems. Electronics 11 20 (Oct. 2022) 3301--3329.
10.3390/electronics11203301
[32]
Wei Xiao Qian Hu Thahir Mohamed Zheng Gao Xibin Gao Radhika Arava and Mohamed AbdelHady. 2022. Two-Stage voice application recommender system for unhandled utterances in intelligent personal assistant. Front. Big Data 5 Article 898050 (Jul. 2022) 12 pages.
10.3389/fdata.2022.898050
[33]
Emre Yalcin. 2022. Exploring potential biases towards blockbuster items in ranking-based recommendations. Data Min. Knowl. Discov. 36 6 (Nov 2022) 2033--2073.
10.1007/s10618-022-00860-1
[34]
L. Yang, Y. Cui, Y. Xuan, C. Wang, S. Belongie, and D. Estrin. 2018. Unbiased offline recommender evaluation for missing-not-at-random implicit feedback. In Proceedings of the 12th ACM Conference on Recommender Systems.
[35]
Christopher C. Johnson. 2014. Logistic matrix factorization for implicit feedback data. Adv. Neural Inf. Process. Syst. 27 (2017) 1--9.
[36]
[37]
Michel Bierlaire. 1998. Discrete Choice Models. Operations Research and Decision Aid Methodologies in Traffic and Transportation Management. Springer, Berlin, 203–227.
10.1007/978-3-662-03514-6_9
[38]
Sebastian Büscher, Manuel Batram, and Dietmar Bauer. 2019. Using motifs for population synthesis in multi-agent mobility simulation models. In Proceedings in Mathematics and Statistics. Springer International, Cham, 335–349.
[39]
Ningyan Chen and Ming Hu. 2023. Data-Driven revenue management: The interplay of data, model, and decision. SSRN Electr. J. (2023).
[40]
Sebastien Lizin Sandra Rousseau Roselinde Kessels Michel Meulders Guido Pepermans Stijn Speelman Martina Vandebroek Goedele Van Den Broeck Ellen J. Van Loo and Wim Verbeke. 2022. The state of the art of discrete choice experiments in food research. Food Qual. Pref. 102 Article 104678 (Dec. 2022) 16 pages.
10.1016/j.foodqual.2022.104678
[41]
Knut Haase. 2009. Discrete location planning.
[42]
Kyosang Hwang Tooba B. Asif and Taesik Lee. 2022. Choice-driven location-allocation model for healthcare facility location problem. Flex. Serv. Manufact. J. 34 4 (Feb. 2022) 1040--1065.
10.1007/s10696-021-09441-8
[43]
Jeffrey E. Harris, Beatriz G. López-Valcárcel, Patricia Barber, and Vicente Ortún. 2014. Efficiency versus equity in the allocation of medical specialty training positions in spain: A Health policy simulation based on a discrete choice model. Working Paper Series. National Bureau of Economic Research.
10.3386/w19896
[44]
David Brain Amarzaya Jadambaa and Sanjeeva Kularatna. 2022. Methodology to derive preference for health screening programmes using discrete choice experiments: A scoping review. BMC Health Serv. Res. 22 1 (Aug. 2022) 1079--1092.
10.1186/s12913-022-08464-7
[45]
Mazen Danaf, Felix Becker, Xiang Song, Bilge Atasoy, and Moshe Ben-Akiva. 2019. Online discrete choice models: Applications in personalized recommendations. Decis. Supp. Syst. 119 (Apr. 2019), 35–45.
10.1016/j.dss.2019.02.003
[46]
Shuang-Hong Yang, Bo Long, Alexander J. Smola, Hongyuan Zha, and Zhaohui Zheng. 2011. Collaborative competitive filtering. In Proceedings of the 34th International ACM SIGIR Conference on Research and Development in Information Retrieval.
[47]
Dawen Liang, Rahul G. Krishnan, Matthew D. Hoffman, and Tony Jebara. 2018. Variational autoencoders for collaborative filtering. In Proceedings of the World Wide Web Conference on World Wide Web.
[48]
Jose Blanchet Guillermo Gallego and Vineet Goyal. 2016. A Markov chain approximation to choice modeling. Operat. Res. 64 4 (Aug. 2016) 886--905.
10.1287/opre.2016.1505
[49]
Moshe Ben-Akiva and Michel Bierlaire. 1999. Discrete choice methods and their applications to short term travel decisions. In International Series in Operations Research and Management Science. Springer, New York, US, 5–33.
[50]
Moshe E. Ben-Akiva and Steven R. Lerman. 1985. Discrete Choice Analysis: Theory and Application to Travel Demand. MIT Press Cambridge MA.
Showing 50 of 107 references
Metrics
9
Citations
107
References
Details
- Published
- Nov 27, 2024
- Vol/Issue
- 3(2)
- Pages
- 1-37
- License
- View
Authors
Funding
Federal Ministry of Education and Research
Award: 21INVI0803
Cite This Article
Thorsten Krause, Alina Deriyeva, Jan H. Beinke, et al. (2024). Mitigating Exposure Bias in Recommender Systems—A Comparative Analysis of Discrete Choice Models. ACM Transactions on Recommender Systems, 3(2), 1-37. https://doi.org/10.1145/3641291
Related
You May Also Like
Heterogeneous Hypergraph Neural Network for Social Recommendation using Attention Network
Bilal Khan, Jia Wu · 2025
45 citations
FedRL: A Reinforcement Learning Federated Recommender System for Efficient Communication Using Reinforcement Selector and Hypernet Generator
Yicheng Di, Hongjian Shi · 2025
42 citations
A Multi-view Graph Contrastive Learning Framework for Cross-Domain Sequential Recommendation
Zhaozhao Xu, Shin-Fu Chen · 2025
13 citations
Communication-Efficient Federated Neural Collaborative Filtering with Multi-Armed Bandits
WAQAR ALI, Muhammad Ammad-Ud-Din · 2025
11 citations