publication
Personalization in Distributed tinyML Applications via Adaptive Clustered Federated Learning
Abstract.
Personalization in Federated Learning (FL) aims to equip each participant with a robust task-specific (personalized) model that is also able to infer from other tasks within the network (generalization). In tinyML applications with model capacity constrains, this personalization vs generalization trade-off is of paramount importance. We showcase a framework with emphasis on personalization, by leveraging Adaptive Clustered Federated Learning, under the constrains imposed by the tinyML setting and based on related research.
Download the full-length Paper
Continue reading about the full details of the approach, the Implementation and the Simulation we conducted as well as the Evaluation for the results.
This paper by A. Filippakopoulos, D. Kastaniotis, Ch. Theocharatos, V. Vassalos has been published in the tinyML Foundation EMEA Innovation Forum (2024).
