Bayesian Modeling of Intersectional Fairness: The Variance of Bias

Friday, August 23, 2019, 11:00 am - 12:00 pm PDTiCal
10th floor conference room (1016)
This event is open to the public.
AI Seminar
James Foulds, UMBC
Video Recording:
With the rising influence of machine learning algorithms on many important aspects of our daily lives, there are growing concerns that biases inherent in data can lead the behavior of these algorithms to discriminate against certain populations.  Informed by the framework of intersectionality from the Humanities literature, we propose mathematical definitions of AI fairness that aim to ensure protection along overlapping dimensions including gender, race, sexual orientation, class, and disability.  We prove that our fairness criteria behave sensibly for any subset of the set of protected attributes, and we illustrate links to differential privacy.  Finally, we present a Bayesian probabilistic modeling approach for the reliable, data-efficient estimation of fairness with multi-dimensional protected attributes.  Experimental results on criminal justice, census, and synthetic data demonstrate the utility of our methodology, and show that Bayesian methods are valuable for the modeling and measurement of fairness in an intersectional context.
Dr. James Foulds is an Assistant Professor in the Department of Information Systems at UMBC.  His research interests are in both applied and foundational machine learning, focusing on probabilistic latent variable models and the inference algorithms to learn them from data.  His work aims to promote the practice of probabilistic modeling for computational social science, and to improve AI's role in society regarding privacy and fairness.  He earned his Ph.D. in computer science at the University of California, Irvine, and was a postdoctoral scholar at the University of California, Santa Cruz, followed by the University of California, San Diego.  His master's and bachelor's degrees were earned with first class honours at the University of Waikato, New Zealand, where he also contributed to the Weka data mining system.
« Return to Upcoming Events