*********************************
There is now a CONTENT FREEZE for Mercury while we switch to a new platform. It began on Friday, March 10 at 6pm and will end on Wednesday, March 15 at noon. No new content can be created during this time, but all material in the system as of the beginning of the freeze will be migrated to the new platform, including users and groups. Functionally the new site is identical to the old one. webteam@gatech.edu
*********************************
Date: Friday, October 21, 2022
Time: 3:00 p.m. - 4:00 p.m.
Location: Centergy One Bldg. CSIP Library, 5th Floor, Technology Square
Virtual: Zoom
Speaker: Venkatesh Saligrama
Speaker’s Title: Professor
Speaker’s Affiliation: Boston University Department of Electrical and Computer Engineering and Department of Computer Science (by courtesy)
Seminar Title: Customizing Federated Learning to the Edge
Abstract: We propose a novel method for federated learning that is customized to the objective of a given edge device. In our proposed method, a server trains a global meta-model by collaborating with devices without actually sharing data. The trained global meta-model is then customized locally by each device to meet its specific objective. Different from the conventional federated learning setting, training customized models for each device is hindered by both the inherent data biases of the various devices, as well as the requirements imposed by the federated architecture. We present an algorithm that locally de- biases model updates, while leveraging distributed data, so that each device can be effectively customized towards its objectives. Our method is fully agnostic to device heterogeneity and imbalanced data, scalable to a massive number of devices, and allows for arbitrary partial participation. Our method has built-in convergence guarantees, and on benchmark datasets we demonstrate that it outperforms other state-of-art methods.
Biographical Sketch of the Speaker: Prof. Venkatesh Saligrama is currently spending this year at Amazon as an Amazon Scholar. He is a faculty member in the Department of Electrical and Computer Engineering, the Department of Computer Science (by courtesy). His research interests are broadly in Artificial Intelligence, and his recent work has focused on machine learning with resource- constraints. He is an IEEE Fellow and recipient of several awards including Distinguished Lecturer for IEEE Signal Processing Society, the Presidential Early Career Award (PECASE), ONR Young Investigator Award, the NSF Career Award. More information about his work is available at https://venkatesh-saligrama.github.io/.
