Federated and distributed learning

Training a shared model across many devices or institutions without pooling their data. These theses cover client selection, personalisation, robustness to malfunctioning or adversarial participants, and the systems work of actually deploying a federation.

11 supervised theses. See all supervised theses for the full list, or open topics if you are looking for one to take on.

Level	Author	Title	Date	Industry	Recording
MSc	G. Argyrou	Byzantine-Robust and Communication-Efficient Federated Fire Detection on Edge Cameras	Aug. 2026	Kudelski IoT	video
MSc	A. Pavlyuk	Federated learning with multi-layer perceptron for sensor drift compensation in direct-ethanol fuel cells	July 2025		video
MSc	P. Dang	Model-Agnostic Personalized Federated Learning using Adaptive Client Selection	Jan. 2025		video
MSc	Q. Luong	Proof of concept for FedRelax on Kubernetes: An implementation guide	Jan. 2025
MSc	S. Monira	FedSock & FedBlue: Scalable decentralized federated learning systems with generalized total variation minimization (GTV-Min)	Nov. 2025
BSc	M. Uusitalo	Error analysis on clustered federated learning	May 2024
MSc	C. Ozen	A collaborative approach for large-scale electricity consumption using federated learning	June 2022
MSc	J. Lillfors	Networked federated learning	July 2022
MSc	Y. Huang	Text analysis of novel coronavirus pneumonia based on federal deep learning	June 2022
MSc	M. Leinonen	Federated multi-task learning over networked data	June 2021
MSc	K. Aalto-Setälä	Optimizing client selection to enhance performance in Federated Learning	in progress