Metraipolis › archive › dc_73f54cbc6f99
A Stable Aggregation Method for Quantum Federated Learning — arXiv:2609.00356
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.00356
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T06:31:48.610Z
- SHA-256 of the archived text
eb12a932bf87f9ca014d334aa0ddccf18c88938ccf16e9dfa43ec16ebeea4ca2- Stable URL of this page
https://metraipolis.com/documento/dc_73f54cbc6f99
How to cite
A Stable Aggregation Method for Quantum Federated Learning — arXiv:2609.00356 — arXiv (en), https://arxiv.org/abs/2609.00356 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_73f54cbc6f99 (Metraipolis archive dc_73f54cbc6f99, sha256 eb12a932bf87f9ca014d334aa0ddccf18c88938ccf16e9dfa43ec16ebeea4ca2)
BibTeX
@misc{dc73f54cbc6f99,
title = {A Stable Aggregation Method for Quantum Federated Learning — arXiv:2609.00356},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.00356},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_73f54cbc6f99; sha256 eb12a932bf87f9ca014d334aa0ddccf18c88938ccf16e9dfa43ec16ebeea4ca2},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00356. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Quantum federated learning (QFL) enables clients to train quantum neural network (QNN) models without sharing private data. We find that aggregation in QFL is unstable under heterogeneous data, unreliable communication, variable fidelity, latency, and quantum hardware noise. Moreover, QFL is non-trivially challenging because several QNN parameters are periodic angles, where Euclidean averaging often fails to capture the inherent dynamics. We develop a novel self-consistent midpoint aggregation method for stable QFL design and implementation. We combine QoS-aware client weighting, circular parameter aggregation, and bounded midpoint-based update control. We perform several angular tests and IBM real Quantum machines experiments for validation confirming our approach. Extensive evaluations and experiments on medical and financial datasets show improved stability, lower volatility, and competitive accuracy. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.00356 — 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 2026-10-17T06:15:12.593Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).