ECE Research Seminar Series: Ermin Wei
Please join the Department of Electrical and Computer Engineering for their Research Seminar Series featuring guest speaker Ermin Wei, an associate professor at Northwestern University, for a presentation on “Flexible and Faithful Federated Learning and Unlearning Methods.” This seminar will take place on Friday, October 6, in room 118 (auditorium) of Siegel Hall from 12:45–1:45 p.m. This event is open to the public.
Federated learning enables machine learning algorithms to be trained over decentralized edge devices without requiring the exchange of local datasets. We consider two scenarios in this talk. In the first scenario, we have cooperative agents running distributed optimization methods. Current literature fails to capture the heterogeneity in agents’ local computation capacities. We propose FedHybrid as a hybrid primal-dual method that allows heterogeneous agents to perform a mixture of first and second order updates. We prove that FedHybrid converges linearly to the exact optimal point for strongly convex functions. In the second scenario, we consider strategic agents with different data distributions. We analyze how the distribution of data affects agents’ incentives to voluntarily participate and obediently follow traditional federated learning algorithms. We design a Faithful Federated Learning (FFL) mechanism based on FedAvg method and VCG mechanism which achieves (probably approximate) optimality, faithful implementation, voluntary participation, and balanced budget. Lastly, we analyze an alternative approach to align individual agent’s incentive to participate by allowing an unlearning option. We propose a multi-stage game theoretic framework and study the equilibrium properties.
Ermin Wei is an associate professor at the electrical and computer engineering department and industrial engineering and management sciences department of Northwestern University. She completed her Ph.D. in electrical engineering and computer science at MIT in 2014, advised by Professor Asu Ozdaglar, where she also obtained her M.S. degree. She received her undergraduate triple degree in computer engineering, finance, and mathematics with a minor in German from University of Maryland, College Park. Her team won the second place in the GO-competition Challenge 1, an electricity grid optimization competition organized by the Department of Energy. Wei’s research interests include distributed optimization methods, convex optimization and analysis, smart grid, communication systems, and energy networks and market economic analysis.