CSH Talk by Alex Jung “Clustered Federated Learning via Generalized Total Variation Minimization”

Alex Jung (Aalto University) will present a talk on Wednesday, September 20th, at 3 PM in Room 201.

Title: Clustered Federated Learning via Generalized Total Variation Minimization

Abstract: We study optimization methods to train local (or personalized) models for decentralized collections of local datasets with an intrinsic network structure. This network structure arises from domain-specific notions of similarity between local datasets. Examples of such notions include spatiotemporal proximity, statistical dependencies, or functional relations. We have recently proposed generalized total variation (GTV) minimization as a main design principle for federated learning from networked data. This formulation unifies and considerably extends existing federated learning methods. By combining techniques from compressed sensing and network flows we can reveal conditions on the local models and the network structure of local datasets such that GTV minimization is able to pool (nearly) homogeneous local datasets.

Bio: Alexander Jung received his Ph.D. (with “sub auspiciis”) in 2012 from TU Vienna. and is currently a tenured Associate Professor for Machine Learning at the Department of Computer Science of Aalto University (Finland). Alex has been chosen as the Computer Science Teacher of the Year at Aalto (2018) and received an Amazon Web Services ML Award (2018). He serves as an Associate Editor of the IEEE Signal Processing Letter and Editorial Board Member of the Machine Learning Journal (Springer). His single-authored textbook “Machine Learning: The Basics” has been published by Springer in 2022.