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

Vasilis Siomos, Sergio Naval-Marimont, Jonathan Passerat-Palmbach, Giacomo Tarroni

City St George's, University of London

We present the first systematic benchmark studying how neural network architectures, initialization strategies, and aggregation methods interact in federated visual classification. Our study spans 5 medical imaging datasets, 12 client sites, and 50K+ images.

IEEE International Symposium on Biomedical Imaging (ISBI) 2024

Abstract

Federated Learning (FL) has emerged as a promising paradigm for training machine learning models on distributed medical imaging data. However, researchers typically evaluate new FL methods by varying one component (e.g., aggregation strategy) while keeping others fixed. This approach overlooks important interactions between components.

ARIA provides the first comprehensive study of how three fundamental FL components—neural network architectures, weight initialization strategies, and aggregation methods—interact with each other. We find that certain combinations that work well in isolation can fail when combined, while other seemingly suboptimal choices can yield strong results together.

Key Findings

Experimental Setup

Our benchmark covers:

Implementation

Our codebase is built on NVIDIA FLARE, providing a production-ready implementation that can be directly deployed in real federated environments. The code includes:

Citation

If you find this work useful, please cite our paper:

@inproceedings{siomos2024aria,
    title={ARIA: On the Interaction Between Architectures, Initialization 
           and Aggregation Methods for Federated Visual Classification},
    author={Siomos, Vasilis and Naval-Marimont, Sergio and 
            Passerat-Palmbach, Jonathan and Tarroni, Giacomo},
    booktitle={IEEE International Symposium on Biomedical Imaging (ISBI)},
    year={2024}
}