HMI DAIS 17 - Public online seminar, 9am 19 August 2021 AEST
Hoda Heidari is currently an Assistant Professor in Machine Learning and Societal Computing at the School of Computer Science, Carnegie Mellon University. She obtained her Ph.D. in Computer and Information Science from the University of Pennsylvania and her M.Sc. degree in Statistics from the Wharton School of Business. Before joining Carnegie Mellon University, she was a postdoctoral fellow at the Machine Learning Institute of ETH Zurich and the AI, Policy, and Practice initiative at Cornell University. Her research is broadly concerned with the societal and economic aspects of Artificial Intelligence. In particular, her work brings together tools and insights from ML, economics, and political philosophy to define and mitigate issues of unfairness and opaqueness through Machine Learning. Her research has won a best-paper award at the ACM Conference on Fairness, Accountability, and Transparency (FAccT) and an exemplary track award at the ACM Conference on Economics and Computation (EC). She has organized several academic events on topics related to responsible and trustworthy AI, including a tutorial at the Web Conference (WWW), and workshops at the Neural and Information Processing Systems (NeurIPS) conference, and the International Conference on Learning Representations (ICLR).
Seminar Title: Fair-ML through the Lens of Equality of Opportunity
Abstract: I begin by presenting a simple mapping between existing mathematical notions of fairness for Machine Learning and models of Equality of opportunity (EOP)—an extensively studied ideal of fairness in political philosophy. Through our conceptual mapping, I will argue that many existing definitions of fairness, such as predictive value parity and equality of odds, can be interpreted as special cases of EOP. In this respect, the EOP interpretation serves as a unifying framework for understanding the normative assumptions underlying existing notions of fairness. Additionally, the EOP view provides a systematic approach for defining new, context-aware mathematical formulations of fairness. I will conclude with a discussion of limitations and directions for future work.