Counterfactual Graph Augmentation for Consumer Unfairness Mitigation in Recommender Systems

TL;DR

This paper introduces a novel method that uses counterfactual explanations to augment user-item interaction graphs, effectively improving fairness in recommender systems while maintaining recommendation utility.

Contribution

It proposes a new approach leveraging counterfactual explanations for graph augmentation to mitigate unfairness in recommendation systems, a novel integration of explainability and fairness techniques.

Findings

Improves fairness-utility trade-off compared to state-of-the-art methods

Effectively identifies unfairness patterns through added edges

Demonstrates effectiveness on two public datasets

Abstract

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.