# Counterfactual Graph Augmentation for Consumer Unfairness Mitigation in Recommender Systems

arXiv: https://arxiv.org/abs/2308.12083 · HTML: https://mlsanity.com/paper/2308.12083/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Aug 2023.

## Built on by (most cited first, 6 of 6)

- [FairDgcl: Fairness-aware Recommendation with Dynamic Graph Contrastive Learning](https://mlsanity.com/paper/2410.17555/) (2024)
- [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)
- [FairTP: A Prolonged Fairness Framework for Traffic Prediction](https://mlsanity.com/paper/2412.16214/) (2024)
- [Fair Augmentation for Graph Collaborative Filtering](https://mlsanity.com/paper/2408.12208/) (2024)
- [Comparative Explanations via Counterfactual Reasoning in Recommendations](https://mlsanity.com/paper/2510.10920/) (2025)

## Abstract (arXiv)

In recommendation literature, explainability and fairness are becoming two prominent perspectives to consider. However, prior works have mostly addressed them separately, for instance by explaining to consumers why a certain item was recommended or mitigating disparate impacts in recommendation utility. None of them has leveraged explainability techniques to inform unfairness mitigation. In this paper, we propose an approach that relies on counterfactual explanations to augment the set of user-item interactions, such that using them while inferring recommendations leads to fairer outcomes. Modeling user-item interactions as a bipartite graph, our approach augments the latter by identifying new user-item edges that not only can explain the original unfairness by design, but can also mitigate it. Experiments on two public data sets show that our approach effectively leads to a better trade-off between fairness and recommendation utility compared with state-of-the-art mitigation procedures. We further analyze the characteristics of added edges to highlight key unfairness patterns. Source code available at https://github.com/jackmedda/RS-BGExplainer/tree/cikm2023.