Counterfactual Graph Augmentation for Consumer Unfairness Mitigation in Recommender Systems
Open Access
- 21 October 2023
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 3753-3757
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.Keywords
All Related Versions
This publication has 18 references indexed in Scilit:
- Explaining recommender systems fairness and accuracy through the lens of data characteristicsInformation Processing & Management, 2021
- Fairness metrics and bias mitigation strategies for rating predictionsInformation Processing & Management, 2021
- DeepFair: Deep Learning for Improving Fairness in Recommender Systems.International Journal of Interactive Multimedia and Artificial Intelligence, 2021
- ELIXIR: Learning from User Feedback on Explanations to Improve Recommender Models2021
- User-oriented Fairness in Recommendation2021
- LightGCN2020
- Explainable Recommendation: A Survey and New PerspectivesFoundations and Trends® in Information Retrieval, 2020
- Neural Graph Collaborative Filtering2019
- The MovieLens DatasetsACM Transactions on Interactive Intelligent Systems, 2015
- A general approximation framework for direct optimization of information retrieval measuresInformation Retrieval Journal, 2009