Our weekly seminar series welcomes Sanmi Koyejo, assistant professor at the University of Illinois at Urbana-Champaign’s Department of Computer Science.
Koyejo's research interests are in developing the principles and practice of adaptive and robust machine learning (ML). Koyejo also focuses on applications to neuroscience and biomedical imaging.
Talk title
“Towards algorithms for measuring and mitigating ML unfairness”
Abstract
It is increasingly evident that widely-deployed machine learning (ML) models can lead to discriminatory outcomes and exacerbate group disparities. The renewed interest in measuring (un)fairness has led to a variety of metrics.
Nevertheless, the measurement problem remains challenging, as existing metrics such as demographic parity may not capture trade-offs relevant to the context at hand, and different fairness definitions can lead to incompatible outcomes.
Metric elicitation is a framework for addressing this metric selection problem—by efficiently estimating implicit preferences from an expert or an expert panel via interactive feedback. I will outline an instance of metric elicitation for measuring group fairness in classification problems. I will also briefly outline some new results on mitigating ML unfairness for multi-class classification with overlapping groups.
Recommended readings
G. Hiranandani, H. Narasimhan, O.O. Koyejo. “Fair Performance Metric Elicitation.” Advances in Neural Information Processing Systems 33, 2020.
F. Yang, M. Cisse, and O.O. Koyejo. “Fairness with Overlapping Groups.” Advances in Neural Information Processing Systems 33, 2020.
Tutorial on Representation Learning and Fairness at NeurIPS 2019.
About Sanmi Koyejo
Sanmi (Oluwasanmi) Koyejo is an Assistant Professor in the Department of Computer Science at the University of Illinois at Urbana-Champaign. Koyejo's research interests are in developing the principles and practice of trustworthy machine learning. Additionally, Koyejo focuses on applications to neuroscience and healthcare. Koyejo completed his Ph.D. in Electrical Engineering at the University of Texas at Austin, advised by Joydeep Ghosh, and completed postdoctoral research at Stanford University. His postdoctoral research was primarily with Russell A. Poldrack and Pradeep Ravikumar. Koyejo has been the recipient of several awards, including a best paper award from the conference on uncertainty in artificial intelligence (UAI), a Skip Ellis Early Career Award, a Sloan Fellowship, a Kavli Fellowship, an IJCAI early career spotlight, and a trainee award from the Organization for Human Brain Mapping (OHBM). Koyejo serves as the president of the Black in AI organization.
About the SRI Seminar Series
The SRI Seminar Series brings together the Schwartz Reisman community and beyond for a robust exchange of ideas that advance scholarship at the intersection of technology and society. Seminars are led by a leading or emerging scholar and feature extensive discussion.
Each week, a featured speaker will present for 45 minutes, followed by 45 minutes of discussion. Registered attendees will be emailed a Zoom link approximately one hour before the event begins. The event will be recorded and posted online.
Sanmi Koyejo