Projects

My research focuses on making federated learning practical — designing architectures, aggregation methods, and training pipelines that work when data is distributed, heterogeneous, and can't be centralized. Below are selected projects; a full publication list follows.

ANFR

TMLR 2025

An Architecture Built for Federated Learning: Addressing Data Heterogeneity through Adaptive Normalization-Free Feature Recalibration

FedCLAM Spotlight

MICCAI 2025

Client-Adaptive Momentum with Foreground Intensity Matching for Federated Medical Image Segmentation

ARIA

IEEE ISBI 2024

On the Interaction Between Architectures, Initialization and Aggregation Methods for Federated Visual Classification

FeRaL

MSc Thesis

A Federated Reinforcement Learning Framework and Library, Applied to Sepsis Treatment

Publications

TMLR 2025
An Architecture Built for Federated Learning: Addressing Data Heterogeneity through Adaptive Normalization-Free Feature Recalibration
Vasilis Siomos, Jonathan Passerat-Palmbach, Giacomo Tarroni
MICCAI 2025
FedCLAM: Client Adaptive Momentum with Foreground Intensity Matching for Federated Medical Image Segmentation
Vasilis Siomos, Jonathan Passerat-Palmbach, Giacomo Tarroni
IEEE ISBI 2024
ARIA: On the Interaction Between Architectures, Initialization and Aggregation Methods for Federated Visual Classification
Vasilis Siomos, Sergio Naval-Marimont, Jonathan Passerat-Palmbach, Giacomo Tarroni