In recent years, personalization research has been delving into issues of explainability and fairness. While some techniques have emerged to provide post-hoc and self-explanatory individual recommendations, there is still a lack of methods aimed at uncovering unfairness in recommendation systems beyond identifying biased user and item features. This paper proposes a new algorithm, GNNUERS, which uses counterfactuals to pinpoint user unfairness explanations in terms of user-item interactions within a bi-partite graph. By perturbing the graph topology, GNNUERS reduces differences in utility between protected and unprotected demographic groups. The paper evaluates the approach using four real-world graphs from different domains and demonstrates its ability to systematically explain user unfairness in three state-of-the-art GNN-based recommendation models. This perturbed network analysis reveals insightful patterns that confirm the nature of the unfairness underlying the explanations. The source code and preprocessed datasets are available at https://github.com/jackmedda/RS-BGExplainer

翻译：近年来，个性化研究已深入探索可解释性与公平性问题。尽管已有若干技术能提供事后的自解释型个体推荐，但在识别推荐系统中超越有偏用户和物品特征的固有偏见方面，仍缺乏有效方法。本文提出一种新算法GNNUERS，通过反事实推理在二分图内精确定位用户-物品交互中的用户不公平性解释。通过扰动图拓扑结构，该方法能降低受保护与非受保护人口群体间的效用差异。本文利用来自不同领域的四个真实图数据评估该方案，并证明其能够系统性地解释三种最新基于图神经网络推荐模型中的用户不公平性。这种扰动网络分析揭示了确认解释背后不公平本质的规律性模式。源代码及预处理数据集已发布于https://github.com/jackmedda/RS-BGExplainer