[ELLIS-DMMLab (CMU) Workshop] Technical challenges of Algorithmic Fairness
Presentation for CMU ResearchersAbstract
Artificial Intelligence are becoming major tools for addressing complex social problems and are also increasingly used to make or support decisions about individuals in many consequential areas of their lives, from justice to healthcare. It is therefore necessary to consider the ethical implications of such decisions, including concepts such as privacy, transparency, accountability, reliability, trustworthiness, autonomy, and fairness. Specifically, we will explain the current landscape of algorithmic fairness in AI, i.e., that algorithms make unbiased decisions without discrimination. I first delved into the mathemathical definitions of fairness, the theory of the current approaches to reach fair decissions. Finally, I explained the 3 main challenges I am addressing in my PhD: data-centric models to understand the impact of fairness constraints in models and data, Graph Fairness and feedback-loops and long-term effects of alforithmic fairness.
In the 2023 ELLIS-DDMLab 3-day workshop, researchers from both laboratories will come together to encourage and develop novel collaborations in the study of human-AI complementarity and the role of AI in human societies. This workshop will be held March 7-9, 2023 in Alicante, Spain.
More information at the CMU official site about ELLIS-DDMLab workshop or ELLIS official site about ELLIS-DDMLab workshop.
The President of the Comunitat Valenciana (Valencian Region, Spain), D. Ximo Puig, visited the event.
Info about CMU’s Dynamic Decision Making Laboratory
The Dynamic Decision Making Laboratory was founded in 2002 by Prof. Cleotilde Gonzalez. Initially supported by a grant from the Army Research Laboratories, the DDMLab is now a group fully funded by grants from research institutions. The focus of the DDMLab research is to develop theoretical understanding of the process by which humans make decisions in dynamic environments and to provide practical demonstrations of how this theoretical knowledge can be used to improve human dynamic decision making and general performance in a number of practical domains from the perspective of cognitive sciences.
Adrián Arnaiz-Rodríguez
Artificial Intelligence PhD Student
ELLIS PhD Student in Algorithmic Fairness and Graph Neural Networks at ELLIS Alicante.