litlas
ログインアカウント作成

User-oriented Fairness in Recommendation

著者: Yunqi Li, Hanxiong Chen, Zuohui Fu, Yingqiang Ge, Yongfeng Zhang - ACM Web Conference, WWW 2021 被引用: 207

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.

Measuring Discriminationin Socially-Sensitive…Measuring Discrimination in Socially-Sensitive Decision RecordsMultisided Fairness forRecommendationMultisided Fairness for RecommendationBeyond Parity: FairnessObjectives for…Beyond Parity: Fairness Objectives for Collaborative FilteringControlling PopularityBias in Learning-to-Ran…Controlling Popularity Bias in Learning-to-Rank RecommendationFairness BeyondDisparate Treatment &…Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate MistreatmentFairness of Exposure inRankingsFairness of Exposure in RankingsTowards a FairMarketplace…Towards a Fair Marketplace: Counterfactual Evaluation of the trade-off between Relevance, Fairness & Satisfaction in Recommendation SystemsThe Unfairness ofPopularity Bias in…The Unfairness of Popularity Bias in RecommendationPolicy Learning forFairness in RankingPolicy Learning for Fairness in RankingFairRec: Two-SidedFairness for…FairRec: Two-Sided Fairness for Personalized Recommendations in Two-Sided PlatformsFairness-AwareExplainable…Fairness-Aware Explainable Recommendation over Knowledge GraphsTowards Long-termFairness in…Towards Long-term Fairness in RecommendationCPFair: PersonalizedConsumer and Producer…CPFair: Personalized Consumer and Producer Fairness Re-ranking for Recommender SystemsA Survey on the Fairnessof Recommender SystemsA Survey on the Fairness of Recommender SystemsExperiments onGeneralizability of…Experiments on Generalizability of User-Oriented Fairness in Recommender SystemsFairness in Ranking,Part II…Fairness in Ranking, Part II: Learning-to-Rank and Recommender SystemsBias and Debias inRecommender System: A…Bias and Debias in Recommender System: A Survey and Future DirectionsThe Unfairness of ActiveUsers and Popularity…The Unfairness of Active Users and Popularity Bias in Point-of-Interest RecommendationFairness inRecommendation…Fairness in Recommendation: Foundations, Methods, and ApplicationsFairness in GraphMining: A SurveyFairness in Graph Mining: A SurveyWhen Fairness meetsBias: a Debiased…When Fairness meets Bias: a Debiased Framework for Fairness aware Top-N RecommendationIn-processing UserConstrained Dominant…In-processing User Constrained Dominant Sets for User-Oriented Fairness in Recommender SystemsA Personalized Frameworkfor Consumer and…A Personalized Framework for Consumer and Producer Group Fairness Optimization in Recommender SystemsDistributionalFairness-aware…Distributional Fairness-aware RecommendationUser-oriented Fairnessin RecommendationUser-oriented Fairness in Recommendation過去の参考文献中心の論文この論文を引用する論文古い新しい

ノードをクリックするとフォーカスを固定、空白をクリックすると本論文に戻ります。ホバーで一時的にプレビューできます。各ノードのページはタイトルから開けます。