User Fairness in Recommender Systems

Leonhardt, Jurek; Anand, Avishek; Khosla, Megha

doi:10.1145/3184558.3186949

Cited by 53 publications

(23 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Beutel et al [7] show how to measure fairness based on pairwise comparisons from randomized experiments, and offer a regularizer to improve fairness when training recommendation models. Leonhardt et al [23] quantify the user unfairness caused by the post-processing algorithms which have the original goal of improving diversity in recommendations. Ge et al [16] explore long-term fairness in recommendation and accomplish the problem through dynamic fairness learning.…”

Section: Fair Recommendationmentioning

confidence: 99%

User-oriented Fairness in Recommendation

Chen

et al. 2021

Proceedings of the Web Conference 2021

126

120

View full text Add to dashboard Cite

As a highly data-driven application, recommender systems could be affected by data bias, resulting in unfair results for different data groups, which could be a reason that affects the system performance. Therefore, it is important to identify and solve the unfairness issues in recommendation scenarios.In this paper, we address the unfairness problem in recommender systems from the user perspective. We group users into advantaged and disadvantaged groups according to their level of activity, and conduct experiments to show that current recommender systems will behave unfairly between two groups of users. Specifically, the advantaged users (active) who only account for a small proportion in data enjoy much higher recommendation quality than those disadvantaged users (inactive). Such bias can also affect the overall performance since the disadvantaged users are the majority. To solve this problem, we provide a re-ranking approach to mitigate this unfairness problem by adding constraints over evaluation metrics. The experiments we conducted on several real-world datasets with various recommendation algorithms show that our approach can not only improve group fairness of users in recommender systems, but also achieve better overall recommendation performance. CCS CONCEPTS• Information systems → Recommender systems; • Computing methodologies → Artificial intelligence.

show abstract

Section: Fair Recommendationmentioning

confidence: 99%

User-oriented Fairness in Recommendation

Chen

et al. 2021

Proceedings of the Web Conference 2021

126

120

View full text Add to dashboard Cite

show abstract

“…Burke [14] and Abdollahpouri and Burke [1] categorized different types of multi-stakeholder platforms and introduced several desired group fairness properties. Leonhardt et al [38] identified the unfairness issue for users in post-processing algorithms to improve the diversity in recommendation. Mehrotra et al [43] proposed a heuristic strategy to jointly optimize fairness and performance in two-sided marketplace platforms.…”

Section: Fair Recommendationmentioning

confidence: 99%

Towards Personalized Fairness based on Causal Notion

Chen

et al. 2021

Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval

View full text Add to dashboard Cite

Recommender systems are gaining increasing and critical impacts on human and society since a growing number of users use them for information seeking and decision making. Therefore, it is crucial to address the potential unfairness problems in recommendations.Just like users have personalized preferences on items, users' demands for fairness are also personalized in many scenarios. Therefore, it is important to provide personalized fair recommendations for users to satisfy their personalized fairness demands. Besides, previous works on fair recommendation mainly focus on associationbased fairness. However, it is important to advance from associative fairness notions to causal fairness notions for assessing fairness more properly in recommender systems. Based on the above considerations, this paper focuses on achieving personalized counterfactual fairness for users in recommender systems. To this end, we introduce a framework for achieving counterfactually fair recommendations through adversary learning by generating featureindependent user embeddings for recommendation. The framework allows recommender systems to achieve personalized fairness for users while also covering non-personalized situations. Experiments on two real-world datasets with shallow and deep recommendation algorithms show that our method can generate fairer recommendations for users with a desirable recommendation performance. CCS CONCEPTS• Computing methodologies → Machine learning; • Information systems → Recommender systems.

show abstract

“…In recommender systems, researchers observed popularity and demographic disparity of the current user-centric applications and recommender systems, with different demographic groups obtain different utility from the recommender systems [8,9,20]. Researchers empirically showed that, the post-processing technique that improves recommendation diversity would amplify user unfairness [22]. Researchers proposed four new metrics for collaborative filtering based recommendation with a binary sensitive attribute, in order to measure the discrepancy between the prediction behavior for disadvantages users and advantaged users.…”

Section: Related Workmentioning

confidence: 99%