Date: Wednesday, April 16th, 2025
11:00 am – 12:00 pm Pacific Time
2:00 pm – 3:00 pm Eastern Time
PLEASE NOTE THE UNUSUAL TIME
Location: Weekly Seminar, Zoom
Title: Incentives for data sharing in federated learning
Abstract:
Federated learning has recently emerged as a powerful approach for enabling collaboration across large populations of learning agents. However, agents may have incentives to defect from the collaboration—that is, to withdraw or contribute less data than expected—due to the costs of data curation and privacy concerns. This raises several key questions: What happens when agents defect, and how can we prevent such defections?
Bio:
Han Shao is currently a CMSA postdoc at Harvard, working with Cynthia Dwork and Ariel Procaccia. She will join UMD CS as an Assistant Professor in Summer 2025. She completed her PhD at TTIC, where she was advised by Avrim Blum. Her research interests span machine learning theory, economics and computation, and algorithmic game theory. During her PhD, she focused on fundamental questions arising from human social and adversarial behaviors in the learning process, examining how these behaviors impact machine learning systems and developing methods to enhance accuracy and robustness. She also explored the theory of adversarial robustness based on empirical observations.