Achieving Fair, Accountable and Transparent Machine Learning Models through Graph Theory and Causality
Adrián Arnaiz-Rodríguez (Ph.D. Student)
Machine learning models are becoming the main tools for addressing complex societal problems and are also increasingly deployed to make or support decisions about individuals in many consequential areas of their lives, from justice to healthcare. Therefore, the ethical implications of such decisions, including concepts such as privacy, transparency, accountability, reliability, autonomy and fairness need to be taken into account. In addition, many of these concepts do not have universally accepted definitions. For example, different fairness definitions might not be able to be satisfied at the same time. In this thesis, we aim to tackle these challenges by leveraging graph theory and causal models to develop individual and group machine learning algorithms and metrics that enhance fairness, accountability, and transparency in algorithmic decision-making.
|Primary Host:||Nuria Oliver (DataPop Alliance, Vodafone Institute & The Spanish Royal Academy of Engineering)|
|Exchange Host:||Manuel Gomez Rodriguez (Max Planck Institute for Software Systems)|
|PhD Duration:||01 November 2021 - 01 November 2024|
|Exchange Duration:||- Ongoing - Ongoing|