[ELLIS Talks - University of Alicante] Fairness in Machine Learning: From introduction to current approaches
PresentationAbstract
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. Specifically, we will explain the current landscape in AI Fairness, from the sources of the bias and different algorithmic fairness approaches to their limitations and cutting-edge approaches. The main goal is to provide a general overview of what is Fairness as well as the main research challenges that the community has to address from a sociotechnical perspective.
Long Talk after 2 months of PhD. The talk in focused on giving a long introduction to the sociotechnical problem of Algorithmic Fairness in Decision Making. This-90 slides presentaion covers broadly the motivation, previous approaches, current approaches and open challenges of the field. In addition, it also cover some sociological and historical concerns about this field, wich is obvoiusly interdisciplinary given the deep importance that it has in ethical and sociological problems.
Adrián Arnaiz-Rodríguez
Artificial Intelligence PhD Student
ELLIS PhD Student in Algorithmic Fairness and Graph Neural Networks at ELLIS Alicante.