Proceedings

Ensuring Reliable and Transparent Algorithmic Fairness Through Optimal Transport and Uncertainty Quantification

Agathe Fernandes Machado

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Doctoral Consortium. Pages 10971-10972.

https://doi.org/10.24963/ijcai.2025/1240

Keywords

  • AI Ethics, Trust, Fairness: ETF: Fairness and diversity
  • AI Ethics, Trust, Fairness: ETF: Trustworthy AI

Abstract

Machine learning (ML) models are increasingly used in high-stakes decisions, such as insurance pricing and pretrial detention, but often reproduce or amplify biases present in data. To mitigate discrimination, optimal transport (OT) offers a principled way to transform unfair model predictions into fair ones while minimizing performance loss. Moreover, uncertainty-based methods like calibration help assess fairness across sensitive groups, while uncertainty attribution helps identify sources of bias. This research aims to address algorithmic fairness challenges by developing evaluation and mitigation techniques with theoretical guarantees from OT, easily deployable in practice, while integrating fairness into the broader framework of trustworthy AI—enhancing calibration and uncertainty attribution methods to ensure ethical use of ML models by transparency and reliability.

Agathe Fernandes Machado. 2025. Ensuring Reliable and Transparent Algorithmic Fairness Through Optimal Transport and Uncertainty Quantification. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 10971–10972. https://doi.org/10.24963/ijcai.2025/1240
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards