Date: Wednesday, July 23, 2025
Time: 2:00 pm - 3:00 pm EDT
Location: DC 1302
Title: Incentivizing Collaboration in Federated Learning
Abstract: Collaborative and federated learning techniques have the potential to enable training powerful machine learning models from distributed data. However, in many cases the potential participants in such collaborative schemes have additional incentives to end-model accuracy. For example, they may be competitors on downstream tasks, they may be concerned about the privacy of their data or they may simply have different data distributions. This creates incentives for individual participants to obfuscate their messages or even damage the training process for the other players, which often undermines the benefits of collaboration. In this talk I will present recent results regarding participation incentives in federated learning (FL). In particular, I will cover several theoretical models for rational data-sharing decision making in the context of market competition, privacy concerns and data heterogeneity. I will also show how to design FL protocols that provably incentivize honesty during training, even in the presence of conflicting incentives.
Bio: Dr. Nikola Konstantinov is a tenure-track faculty member of INSAIT, in Sofia, Bulgaria. He is also a member of the ELLIS Society. His research interests lie in the area of trustworthy machine learning, in particular robust and incentive-aware machine learning. Before joining INSAIT, he was a postdoctoral fellow at the ETH AI Center, working under the supervision of Prof. Martin Vechev and Prof. Fanny Yang. Prior to that, he was a PhD student at IST Austria, working in the group of Prof. Christoph Lampert. He was also part of the ELLIS PhD Program.