QFL-Adaptive: Uma Abordagem Híbrida de Aprendizado Federado Quântico Personalizado e Resiliente

• Rómulo W. C. Bustincio UNICAMP https://orcid.org/0000-0002-3971-5105
• Edgar C. Pozo Universidad de Guanajuato https://orcid.org/0000-0002-4120-8495
• Ricardo J. Hancco-Ancori Universidad Nacional de San Agustín de Arequipa https://orcid.org/0000-0001-8308-4833
• Francisco Airton Silva UFPI https://orcid.org/0000-0002-8211-6060
• Allan M. de Souza UFPI https://orcid.org/0000-0002-5518-8392
• Luiz F. Bittencourt UFPI https://orcid.org/0000-0001-6305-9059

DOI: https://doi.org/10.5753/sbrc.2026.19918

Resumo

O Aprendizado Federado Quântico (QFL) surge como um paradigma para o treinamento distribuído com preservação de privacidade. No entanto, sua implementação prática na era Noisy Intermediate-Scale Quantum (NISQ) enfrenta barreiras críticas: a sobrecarga de comunicação e a deriva do modelo causada por dados Non-Independent and Identically Distributed (Non-IID). Este trabalho propõe o QFL-Adaptive, um framework que integra uma arquitetura segmentada inspirada em VQC com agregação personalizada via Weighted Personalized QFL (wp-QFL). A arquitetura segue uma segmentação pole-angle inspirada em Circuitos Quânticos Variacionais (VQC), separando parâmetros de Ângulo (ϕ) e Polo (θ), permitindo o ajuste dinâmico da carga de transmissão via uplink condicional baseado na telemetria do canal. Resultados em quatro datasets demonstram economia de banda de 77,81% e retenção de acurácia superior a 97,9% sob 80% de falha comunicacional. Validações em hardware quântico real são fundamentais para confirmar a eficácia sob ruído de decoerência.

Referências

Ballester, R., Cerquides, J., and Artiles, L. (2025). Quantum federated learning: a comprehensive literature review of foundations, challenges, and future directions. Quantum Machine Intelligence, 7(73).

Broughton, M. et al. (2021). Tensorflow quantum: A software framework for quantum machine learning. arXiv preprint arXiv:2003.02989.

Cerezo, M. et al. (2022). Challenges and opportunities in quantum machine learning. Nature Computational Science, 2:567–576.

Chehimi, M., Chen, S. Y.-C., Saad, W., Towsley, D., and Debbah, M. (2024). Foundations of quantum federated learning over classical and quantum networks. IEEE Network, 38(1):124–130.

Chehimi, M. and Saad, W. (2022). Quantum federated learning with quantum data. ICASSP 2022, pages 8617–8621.

Chen, S. Y.-C. and Yoo, S. (2021). Federated quantum machine learning. Entropy, 23(4):460.

Gurung, D. and Pokhrel, S. R. (2024). A personalized quantum federated learning. In Proceedings of the 8th Asia-Pacific Workshop on Networking, APNet ’24, page 175–176, New York, NY, USA. Association for Computing Machinery.

Gurung, D. and Pokhrel, S. R. (2025). Performance analysis and design of a weighted personalized quantum federated learning. IEEE Transactions on Artificial Intelligence. DOI: 10.1109/TAI.2025.3545393.

Havlíček, V., Córcoles, A. D., Temme, K., Harrow, A. W., Kandala, A., Chow, J. M., and Gambetta, J. M. (2019). Supervised learning with quantum-enhanced feature spaces. Nature, 567(7747):209–212.

Illiano, J., Caleffi, M., Manzalini, A., and Cacciapuoti, A. S. (2022). Quantum internet protocol stack: A comprehensive survey. Comput. Netw., 213(C).

Liu, C.-Y. and Chen, S. Y.-C. (2024). Federated quantum-train with batched parameter generation. arXiv preprint arXiv:2409.02763.

McMahan, H. B., Moore, E., Ramage, D., Hampson, S., and Agüera y Arcas, B. (2017). Communication-efficient learning of deep networks from decentralized data. In Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, AISTATS, pages 1273–1282.

Nguyen, D. C. et al. (2025). Quantum federated learning: A comprehensive survey. IEEE Communications Surveys and Tutorials.

Nielsen, M. A. and Chuang, I. L. (2010). Quantum Computation and Quantum Information. Cambridge University Press, 10th anniversary edition.

Park, S., Lee, H., Son, S. B., Jung, S., and Kim, J. (2025). Quantum federated learning with pole-angle quantum local training and trainable measurement. Neural Networks, 187:107301.

Preskill, J. (2018). Quantum computing in the nisq era and beyond. Quantum, 2:79.

Qi, J. and Hsieh, M.-H. (2024). Federated quantum natural gradient descent for quantum federated learning. In Federated Learning, pages 329–341. Elsevier.

Qi, J., Zhang, X.-L., and Tejedor, J. (2023). Optimizing quantum federated learning based on federated quantum natural gradient descent. In ICASSP 2023.

Thompson, N. C., Greenewald, K., Lee, K., and Manso, G. F. (2020). The computational limits of deep learning. arXiv preprint arXiv:2007.05558.

Yun, W. J. et al. (2022). Slimmable quantum federated learning. arXiv preprint arXiv:2207.10221.

Zhao, H. (2023). Non-iid quantum federated learning with one-shot communication complexity. Quantum Machine Intelligence, 5(1):3.