Data-Aware Layer Assignment for Secure and Efficient Communication in Federated Learning for Medical Image Analysis
Proceedings of the AAAI Symposium Series · 23.11.2025 · 7 (1) · 516-523
DOI: 10.1609/aaaiss.v7i1.36926 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Symposium Series, online erschienen am 23.11.2025. Verfasst von Sai Sriram Gonthina und 4 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref).
Abstract (Originalsprache)
Cross-silo medical imaging federations must contend with strict privacy, limited bandwidth, and non identically distributed (non-IID) data that destabilize training. Current federated learning (FL) architectures either carry the full model (e.g., FedAvg/FedProx) or use naive client/layer pruning and random sampling while ignoring both non-IID heterogeneity and per-layer utility. Based on these limitations, the paper presents a dataaware, layer-wise protocol that aligns communication with expected loss descent while bounding per-round client leverage. Each round, the server estimates per-layer influence from a tiny root set, and clients expose lightweight metadata to form data-quality scores. A capacity-constrained entropic transport matches high-influence layers to high-quality clients under redundancy and temporal coverage. Clients train all layers but upload exactly one with train-all, send-one principle. The server then performs per-layer robust aggregation on masked updates via secure aggregation. On the three cross-silo imaging benchmarks of Pneumonia CXR, Brain-Tumor MRI, and ISIC Skin Cancer, it demonstrates a strong threshold free detection quality (AUROC/ AUPRC: 0.925/0.935, 0.996/0.988, 0.834/0.852, respectively) while also reducing the per round up-link by ≈ 1/n with respect to FedAvg (e.g., ≈ 10× with 10 clients) by only receiving one layer per client. Indicating its viability for deployment-grade secure aggregation for hospital networks.
Zitieren
APA
Gonthina, S. S., Roy, S., Bhattacharya, P., Rana, P., & Shetty, S. (2025). Data-Aware Layer Assignment for Secure and Efficient Communication in Federated Learning for Medical Image Analysis. Proceedings of the AAAI Symposium Series, 7(1), 516-523. https://doi.org/10.1609/aaaiss.v7i1.36926
Vancouver
Gonthina SS, Roy S, Bhattacharya P, Rana P, Shetty S. Data-Aware Layer Assignment for Secure and Efficient Communication in Federated Learning for Medical Image Analysis. Proceedings of the AAAI Symposium Series. 2025;7(1):516-523. doi:10.1609/aaaiss.v7i1.36926
BibTeX
@article{Gonthina2025,
author = {Gonthina, Sai Sriram and Roy, Sandip and Bhattacharya, Pronaya and Rana, Pratip and Shetty, Sachin},
title = {Data-Aware Layer Assignment for Secure and Efficient Communication in Federated Learning for Medical Image Analysis},
journal = {Proceedings of the AAAI Symposium Series},
year = {2025},
volume = {7},
number = {1},
pages = {516--523},
doi = {10.1609/aaaiss.v7i1.36926}
}
EUVIMED