Metraipolis › archive › dc_0efeb8a68ab4

Performance Benchmarking of Federated Learning Frameworks for Medical Image Classification — arXiv:2611.10688

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.10688
License (as archived): CC0-1.0
Archived: 2026-11-10T18:45:42.081Z
SHA-256 of the archived text: 98d95b9f01d4309b85f69476b9e3c04fccd4fff2797ba1402906ca8cb1af260e
Stable URL of this page: https://metraipolis.com/documento/dc_0efeb8a68ab4

How to cite

Performance Benchmarking of Federated Learning Frameworks for Medical Image Classification — arXiv:2611.10688 — arXiv (en), https://arxiv.org/abs/2611.10688 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0efeb8a68ab4 (Metraipolis archive dc_0efeb8a68ab4, sha256 98d95b9f01d4309b85f69476b9e3c04fccd4fff2797ba1402906ca8cb1af260e)

BibTeX

@misc{dc0efeb8a68ab4,
  title = {Performance Benchmarking of Federated Learning Frameworks for Medical Image Classification — arXiv:2611.10688},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.10688},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0efeb8a68ab4; sha256 98d95b9f01d4309b85f69476b9e3c04fccd4fff2797ba1402906ca8cb1af260e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.10688. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Selecting a Federated Learning (FL) framework requires understanding the resource demands of its training and evaluation workflow. This work compares Flower, NVIDIA FLARE, and FedBioMed using two-dimensional MedNIST classification with ResNet-10 in a containerized, single-host environment. Following a dated review of repository activity and documented medical applications, we evaluated nine configurations per framework, with three random seeds, for a total of 81 executions. The configurations varied federation size, communication rounds, and batch size. We monitored execution time, CPU and RAM consumption, host-level GPU utilization, server network traffic rates, and model accuracy at the end of each execution. The implementations shared nominal learning settings while retaining differences in data splitting and federated evaluation. Configuration-blocked non-parametric analysis identified differences in execution time, client and server memory, GPU utilization, and network traffic rates. NVIDIA FLARE exhibited the lowest server-memory consumption and the highest host-level GPU utilization, Flower exhibited the highest average server network traffic rate, and FedBioMed required more client memory and longer execution time. No statistically significant difference in final accuracy was detected within the evaluated short training schedules; this does not establish convergence or equivalent predictive performance. The results characterize the configured workflows under shared hardware resources. They provide a concrete case study of system behavior, with conclusions bounded by workflow asymmetries, local networking, and the lightweight MedNIST workload.

Tema degli esploratori: calcolo e infrastrutture (elenco arXiv cs.DC, nuovi lavori del giorno).
Categorie arXiv: Distributed, Parallel, and Cluster Computing (cs.DC) ; Performance (cs.PF).
Pagina del lavoro: https://arxiv.org/abs/2611.10688 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-10T18:38:07.439Z dalla pagina https://arxiv.org/list/cs.DC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).