AoI-U: Uma Análise do Trade-off entre Fairness Temporal e Utilidade Estatística na Seleção de Clientes em Aprendizado Federado
Resumo
O trabalho analisa como políticas de seleção de clientes afetam o aprendizado federado (AF) sob dados não-IID, explorando o trade-off entre fairness temporal (via Age of Information, AoI) e utilidade estatística (via entropia das predições). Propõe-se o framework AoI-U, que combina ambos os critérios com um parâmetro α. Experimentos com CIFAR-10 mostram que AoI gera participação uniforme, entropia concentra atualizações e o método misto reduz desigualdade mantendo desempenho competitivo. Embora as acurácias finais sejam semelhantes, as trajetórias de convergência diferem. Os resultados indicam que fairness e utilidade interagem de forma não trivial e influenciam a dinâmica do AF.Referências
Beluch, W. H., Genewein, T., Nurnberger, A., and Kohler, J. M. (2018). The power of ensembles for active learning in image classification. In 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9368–9377.
Beutel, D. J., Topal, T., Mathur, A., Qiu, X., Fernandez-Marques, J., Gao, Y., Sani, L., Li, K. H., Parcollet, T., De Gusmão, P. P. B., et al. (2020). Flower: A friendly federated learning research framework. arXiv preprint arXiv:2007.14390.
Cavalcante, I. C., Meneguette, R. I., Torres, R. H., Mano, L. Y., Gonçalves, V. P., Ueyama, J., Pessin, G., Amvame Nze, G. D., and Rocha Filho, G. P. (2022). Federated system for transport mode detection. Energies, 15(23):9256.
Cho, Y. J., Wang, J., and Joshi, G. (2020). Client selection in federated learning: Convergence analysis and power-of-choice selection strategies. arXiv preprint arXiv:2010.01243.
de Oliveira, J. A., Gonçalves, V. P., Meneguette, R. I., de Sousa Jr, R. T., Guidoni, D. L., Oliveira, J. C., and Rocha Filho, G. P. (2023). F-nids—a network intrusion detection system based on federated learning. Computer Networks, 236:110010.
Kairouz, P. and McMahan, H. B. (2021). Advances and open problems in federated learning. Foundations and Trends in Machine Learning, 14(1-2):1–210.
Kaul, S., Yates, R., and Gruteser, M. (2012). Real-time status: How often should one update? In 2012 Proceedings IEEE INFOCOM, pages 2731–2735.
Lai, F., Zhu, X., Madhyastha, H. V., and Chowdhury, M. (2021). Oort: Efficient federated learning via guided participant selection. In 15th {USENIX} Symposium on Operating Systems Design and Implementation ({OSDI} 21), pages 19–35.
Li, Q., Wen, Z., Wu, Z., Hu, S., Wang, N., Li, Y., Liu, X., and He, B. (2023). A survey on federated learning systems: Vision, hype and reality for data privacy and protection. IEEE Transactions on Knowledge and Data Engineering, 35(4):3347–3366.
Li, T., Sahu, A. K., Zaheer, M., Sanjabi, M., Talwalkar, A., and Smith, V. (2020). Federated optimization in heterogeneous networks. Proceedings of Machine learning and systems, 2:429–450.
McMahan, B., Moore, E., Ramage, D., Hampson, S., and y Arcas, B. A. (2017). Communication-efficient learning of deep networks from decentralized data. In Artificial intelligence and statistics, pages 1273–1282. PMLR.
Nishio, T. and Yonetani, R. (2019). Client selection for federated learning with heterogeneous resources in mobile edge. In ICC 2019-2019 IEEE international conference on communications (ICC), pages 1–7. IEEE.
Settles, B. (2009). Active learning literature survey. Technical report, University of Wisconsin–Madison.
Sun, Y., Kadota, I., Talak, R., and Modiano, E. (2022). Age of information: A new metric for information freshness. Springer Nature.
Uddin, M. P., Xiang, Y., Hasan, M., Bai, J., Zhao, Y., and Gao, L. (2025). A systematic literature review of robust federated learning: Issues, solutions, and future research directions. ACM Comput. Surv., 57(10).
Wang, H., Kaplan, Z., Niu, D., and Li, B. (2020). Optimizing federated learning on non-iid data with reinforcement learning. In IEEE INFOCOM 2020 - IEEE Conference on Computer Communications, pages 1698–1707.
Yang, H. H., Arafa, A., Quek, T. Q. S., and Vincent Poor, H. (2020). Age-based scheduling policy for federated learning in mobile edge networks. In ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 8743–8747.
Beutel, D. J., Topal, T., Mathur, A., Qiu, X., Fernandez-Marques, J., Gao, Y., Sani, L., Li, K. H., Parcollet, T., De Gusmão, P. P. B., et al. (2020). Flower: A friendly federated learning research framework. arXiv preprint arXiv:2007.14390.
Cavalcante, I. C., Meneguette, R. I., Torres, R. H., Mano, L. Y., Gonçalves, V. P., Ueyama, J., Pessin, G., Amvame Nze, G. D., and Rocha Filho, G. P. (2022). Federated system for transport mode detection. Energies, 15(23):9256.
Cho, Y. J., Wang, J., and Joshi, G. (2020). Client selection in federated learning: Convergence analysis and power-of-choice selection strategies. arXiv preprint arXiv:2010.01243.
de Oliveira, J. A., Gonçalves, V. P., Meneguette, R. I., de Sousa Jr, R. T., Guidoni, D. L., Oliveira, J. C., and Rocha Filho, G. P. (2023). F-nids—a network intrusion detection system based on federated learning. Computer Networks, 236:110010.
Kairouz, P. and McMahan, H. B. (2021). Advances and open problems in federated learning. Foundations and Trends in Machine Learning, 14(1-2):1–210.
Kaul, S., Yates, R., and Gruteser, M. (2012). Real-time status: How often should one update? In 2012 Proceedings IEEE INFOCOM, pages 2731–2735.
Lai, F., Zhu, X., Madhyastha, H. V., and Chowdhury, M. (2021). Oort: Efficient federated learning via guided participant selection. In 15th {USENIX} Symposium on Operating Systems Design and Implementation ({OSDI} 21), pages 19–35.
Li, Q., Wen, Z., Wu, Z., Hu, S., Wang, N., Li, Y., Liu, X., and He, B. (2023). A survey on federated learning systems: Vision, hype and reality for data privacy and protection. IEEE Transactions on Knowledge and Data Engineering, 35(4):3347–3366.
Li, T., Sahu, A. K., Zaheer, M., Sanjabi, M., Talwalkar, A., and Smith, V. (2020). Federated optimization in heterogeneous networks. Proceedings of Machine learning and systems, 2:429–450.
McMahan, B., Moore, E., Ramage, D., Hampson, S., and y Arcas, B. A. (2017). Communication-efficient learning of deep networks from decentralized data. In Artificial intelligence and statistics, pages 1273–1282. PMLR.
Nishio, T. and Yonetani, R. (2019). Client selection for federated learning with heterogeneous resources in mobile edge. In ICC 2019-2019 IEEE international conference on communications (ICC), pages 1–7. IEEE.
Settles, B. (2009). Active learning literature survey. Technical report, University of Wisconsin–Madison.
Sun, Y., Kadota, I., Talak, R., and Modiano, E. (2022). Age of information: A new metric for information freshness. Springer Nature.
Uddin, M. P., Xiang, Y., Hasan, M., Bai, J., Zhao, Y., and Gao, L. (2025). A systematic literature review of robust federated learning: Issues, solutions, and future research directions. ACM Comput. Surv., 57(10).
Wang, H., Kaplan, Z., Niu, D., and Li, B. (2020). Optimizing federated learning on non-iid data with reinforcement learning. In IEEE INFOCOM 2020 - IEEE Conference on Computer Communications, pages 1698–1707.
Yang, H. H., Arafa, A., Quek, T. Q. S., and Vincent Poor, H. (2020). Age-based scheduling policy for federated learning in mobile edge networks. In ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 8743–8747.
Publicado
25/05/2026
Como Citar
SANTANA, Andher P. Capanema; ROCHA FILHO, Geraldo P..
AoI-U: Uma Análise do Trade-off entre Fairness Temporal e Utilidade Estatística na Seleção de Clientes em Aprendizado Federado. In: SIMPÓSIO BRASILEIRO DE REDES DE COMPUTADORES E SISTEMAS DISTRIBUÍDOS (SBRC), 44. , 2026, Praia do Forte/BA.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 225-238.
ISSN 2177-9384.
DOI: https://doi.org/10.5753/sbrc.2026.19935.
