QFI‐Opt: Communication‐Efficient Quantum Federated Learning via Quantum Fisher Information
Software: Practice and Experience · 2026-03 · 56 (3) · 289-316
DOI: 10.1002/spe.70048 ↗Kurz gefasst
Fachartikel in der Zeitschrift Software: Practice and Experience, online erschienen am 21.12.2025. Verfasst von Rui Zhang und 7 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 68 Literaturangaben. Gefördert von: Natural Science Foundation of Jiangsu Province.
Abstract (Originalsprache)
Background
Quantum federated learning presents a promising paradigm for privacy‐preserving collaborative training across distributed quantum devices. However, its scalability is hindered by the significant communication overhead associated with transmitting high‐dimensional, high‐precision quantum model parameters over classical networks.
Methods
To address this bottleneck, this paper proposes QFI‐Opt (Quantum Fisher Information‐guided Adaptive Optimization), a quantum adaptive communication optimization framework based on Quantum Fisher Information. QFI‐Opt establishes a “sensing‐compression‐regulation” pipeline that achieves communication efficiency while preserving quantum model fidelity. The framework uses QFI as a physically interpretable metric to dynamically assess quantum state sensitivity to parameter perturbations, enabling a progressive pruning strategy that removes low‐sensitivity parameters during training while retaining critical quantum features. Additionally, a dynamic bit‐width quantization mechanism adapts precision based on parameter importance, maximizing compression without compromising numerical stability. This is further complemented by a physics‐aware aggregation method that weighs client updates based on both local data volume and quantum information quality derived from QFI scores, improving global model robustness.
Results
Extensive evaluation on quantum convolutional neural networks demonstrates that QFI‐Opt significantly reduces per‐round communication overhead compared to baseline methods.
Conclusions
Simultaneously, the proposed framework maintains competitive model accuracy and convergence performance across diverse quantum architectures.
Förderung
- Natural Science Foundation of Jiangsu Province
Zitieren
APA
Zhang, R., Wang, Y., He, X., Cai, Z., Di, Y., Bao, J., Fan, J., & Qu, Z. (2026). QFI‐Opt: Communication‐Efficient Quantum Federated Learning via Quantum Fisher Information. Software: Practice and Experience, 56(3), 289-316. https://doi.org/10.1002/spe.70048
Vancouver
Zhang R, Wang Y, He X, Cai Z, Di Y, Bao J, et al. QFI‐Opt: Communication‐Efficient Quantum Federated Learning via Quantum Fisher Information. Software: Practice and Experience. 2026;56(3):289-316. doi:10.1002/spe.70048
BibTeX
@article{Zhang2026,
author = {Zhang, Rui and Wang, Yueheng and He, Xing and Cai, Zinuo and Di, Yicheng and Bao, Jiayu and Fan, Jiansong and Qu, Zhongle},
title = {QFI‐Opt: Communication‐Efficient Quantum Federated Learning via Quantum Fisher Information},
journal = {Software: Practice and Experience},
year = {2026},
volume = {56},
number = {3},
pages = {289--316},
doi = {10.1002/spe.70048}
}
EUVIMED