User-oriented Fairness in Recommendation

Abstract

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.

Accepted to the 30th Web Conference (WWW 2021)

References in corpus (18)

• BPR: Bayesian Personalized Ranking from Implicit Feedback
• Equality of Opportunity in Supervised Learning
• Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment
• Fairness of Exposure in Rankings
• Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches
• Towards Long-term Fairness in Recommendation
• FairRec: Two-Sided Fairness for Personalized Recommendations in Two-Sided Platforms
• Learning Non-Discriminatory Predictors
• Beyond Parity: Fairness Objectives for Collaborative Filtering
• Managing Popularity Bias in Recommender Systems with Personalized Re-ranking
• Satisfying Real-world Goals with Dataset Constraints
• The Unfairness of Popularity Bias in Recommendation
• A Reductions Approach to Fair Classification
• Multisided Fairness for Recommendation
• Policy Learning for Fairness in Ranking
• Multi-stakeholder Recommendation and its Connection to Multi-sided Fairness
• Fairness-Aware Explainable Recommendation over Knowledge Graphs
• Graph Clustering Bandits for Recommendation

Cited by in corpus (29)

• A Survey on the Fairness of Recommender Systems
• A Comprehensive Survey on Deep Graph Representation Learning
• Fairness in Recommender Systems: Research Landscape and Future Directions
• Personalized Counterfactual Fairness in Recommendation
• Is ChatGPT Fair for Recommendation? Evaluating Fairness in Large Language Model Recommendation
• Toward Pareto Efficient Fairness-Utility Trade-off inRecommendation through Reinforcement Learning
• Explainable Fairness in Recommendation
• Invariant Collaborative Filtering to Popularity Distribution Shift
• Consumer Fairness in Recommender Systems: Contextualizing Definitions and Mitigations
• DVR: Micro-Video Recommendation Optimizing Watch-Time-Gain under Duration Bias
• AI Ethics: A Bibliometric Analysis, Critical Issues, and Key Gaps
• Learning Informative Representation for Fairness-aware Multivariate Time-series Forecasting: A Group-based Perspective
• Intersectional Two-sided Fairness in Recommendation
• Exploring the Impact of Temporal Bias in Point-of-Interest Recommendation
• Investigating the Robustness of Sequential Recommender Systems Against Training Data Perturbations
• Unmasking Gender Bias in Recommendation Systems and Enhancing Category-Aware Fairness
• Causality-Inspired Fair Representation Learning for Multimodal Recommendation
• Integrity and Junkiness Failure Handling for Embedding-based Retrieval: A Case Study in Social Network Search
• FairSort: Learning to Fair Rank for Personalized Recommendations in Two-Sided Platforms
• Fairness-aware Differentially Private Collaborative Filtering
• In-processing User Constrained Dominant Sets for User-Oriented Fairness in Recommender Systems
• Automatic Feature Fairness in Recommendation via Adversaries
• Mitigating Mainstream Bias in Recommendation via Cost-sensitive Learning
• Countering Mainstream Bias via End-to-End Adaptive Local Learning
• Problem Learning: Towards the Free Will of Machines
• Evaluating and Addressing Fairness Across User Groups in Negative Sampling for Recommender Systems
• Guaranteeing Accuracy and Fairness under Fluctuating User Traffic: A Bankruptcy-Inspired Re-ranking Approach
• Doing Data Right: How Lessons Learned Working with Conventional Data should Inform the Future of Synthetic Data for Recommender Systems
• Recommendation Fairness in Social Networks Over Time