# GNNUERS: Fairness Explanation in GNNs for Recommendation via Counterfactual Reasoning

arXiv: https://arxiv.org/abs/2304.06182 · HTML: https://mlsanity.com/paper/2304.06182/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Apr 2023.

## Built on by (most cited first, 7 of 7)

- [Fairness-Aware Graph Neural Networks: A Survey](https://mlsanity.com/paper/2307.03929/) (2023)
- [How Fair is Your Diffusion Recommender Model?](https://mlsanity.com/paper/2409.04339/) (2024)
- [On Explaining Unfairness: An Overview](https://mlsanity.com/paper/2402.10762/) (2024)
- [Unmasking Gender Bias in Recommendation Systems and Enhancing Category-Aware Fairness](https://mlsanity.com/paper/2502.17921/) (2025)
- [Fair Augmentation for Graph Collaborative Filtering](https://mlsanity.com/paper/2408.12208/) (2024)
- [Explaining Group Recommendations via Counterfactuals](https://mlsanity.com/paper/2601.16882/) (2026)
- [Explaining Synergistic Effects in Social Recommendations](https://mlsanity.com/paper/2601.18151/) (2026)

## Abstract (arXiv)

Nowadays, research into personalization has been focusing on explainability and fairness. Several approaches proposed in recent works are able to explain individual recommendations in a post-hoc manner or by explanation paths. However, explainability techniques applied to unfairness in recommendation have been limited to finding user/item features mostly related to biased recommendations. In this paper, we devised a novel algorithm that leverages counterfactuality methods to discover user unfairness explanations in the form of user-item interactions. In our counterfactual framework, interactions are represented as edges in a bipartite graph, with users and items as nodes. Our bipartite graph explainer perturbs the topological structure to find an altered version that minimizes the disparity in utility between the protected and unprotected demographic groups. Experiments on four real-world graphs coming from various domains showed that our method can systematically explain user unfairness on three state-of-the-art GNN-based recommendation models. Moreover, an empirical evaluation of the perturbed network uncovered relevant patterns that justify the nature of the unfairness discovered by the generated explanations. The source code and the preprocessed data sets are available at https://github.com/jackmedda/RS-BGExplainer.