Explainable Fairness in Recommendation

Abstract

Existing research on fairness-aware recommendation has mainly focused on the quantification of fairness and the development of fair recommendation models, neither of which studies a more substantial problem--identifying the underlying reason of model disparity in recommendation. This information is critical for recommender system designers to understand the intrinsic recommendation mechanism and provides insights on how to improve model fairness to decision makers. Fortunately, with the rapid development of Explainable AI, we can use model explainability to gain insights into model (un)fairness. In this paper, we study the problem of explainable fairness, which helps to gain insights about why a system is fair or unfair, and guides the design of fair recommender systems with a more informed and unified methodology. Particularly, we focus on a common setting with feature-aware recommendation and exposure unfairness, but the proposed explainable fairness framework is general and can be applied to other recommendation settings and fairness definitions. We propose a Counterfactual Explainable Fairness framework, called CEF, which generates explanations about model fairness that can improve the fairness without significantly hurting the performance.The CEF framework formulates an optimization problem to learn the "minimal" change of the input features that changes the recommendation results to a certain level of fairness. Based on the counterfactual recommendation result of each feature, we calculate an explainability score in terms of the fairness-utility trade-off to rank all the feature-based explanations, and select the top ones as fairness explanations.

In Proceedings of SIGIR 2022

References in corpus (21)

• Reinforcement Knowledge Graph Reasoning for Explainable Recommendation
• User-oriented Fairness in Recommendation
• Towards Long-term Fairness in Recommendation
• Personalized Counterfactual Fairness in Recommendation
• Counterfactual Explainable Recommendation
• Understanding Echo Chambers in E-commerce Recommender Systems
• From Parity to Preference-based Notions of Fairness in Classification
• Learning and Evaluating Graph Neural Network Explanations based on Counterfactual and Factual Reasoning
• CAFE: Coarse-to-Fine Neural Symbolic Reasoning for Explainable Recommendation
• Neural Collaborative Reasoning
• Generate Natural Language Explanations for Recommendation
• Maximizing Marginal Fairness for Dynamic Learning to Rank
• Graph Collaborative Reasoning
• Causal Collaborative Filtering
• Explainability for fair machine learning
• Learning Personalized Risk Preferences for Recommendation
• AutoLossGen: Automatic Loss Function Generation for Recommender Systems
• Variation Control and Evaluation for Generative SlateRecommendations
• Try This Instead: Personalized and Interpretable Substitute Recommendation
• Pareto Efficient Fairness in Supervised Learning: From Extraction to Tracing
• Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)

Cited by in corpus (5)

• Attention Is Not the Only Choice: Counterfactual Reasoning for Path-Based Explainable Recommendation
• A Critical Survey on Fairness Benefits of Explainable AI
• Counterfactual Collaborative Reasoning
• Dynamic Causal Collaborative Filtering
• Vertical Allocation-based Fair Exposure Amortizing in Ranking