Federated Learning (FL) is a distributed approach to collaboratively training machine learning models. FL requires a high level of communication between the devices and a central server, thus imposing several challenges, including communication bottlenecks and network scalability. This article introduces ACSP-FL (https://github.com/AllanMSouza/ACSP-FL), a solution to reduce the overall communication and computation costs for training a model in FL environments. ACSP-FL employs a client selection strategy that dynamically adapts the number of devices training the model and the number of rounds required to achieve convergence. Moreover, ACSP-FL enables model personalization to improve clients performance. A use case based on human activity recognition datasets aims to show the impact and benefits of ACSP-FL when compared to state-of-the-art approaches. Experimental evaluations show that ACSP-FL minimizes the overall communication and computation overheads to train a model and converges the system efficiently. In particular, ACSP-FL reduces communication up to 95% compared to literature approaches while providing good convergence even in scenarios where data is distributed differently, non-independent and identical way between client devices.

翻译：联邦学习（Federated Learning, FL）是一种用于协同训练机器学习模型的分布式方法。FL 需要在设备与中央服务器之间进行大量通信，因此带来了若干挑战，包括通信瓶颈和网络可扩展性问题。本文介绍了 ACSP-FL (https://github.com/AllanMSouza/ACSP-FL)，一种旨在降低 FL 环境中模型训练总体通信与计算成本的解决方案。ACSP-FL 采用一种客户端选择策略，该策略能动态调整参与模型训练的客户端数量以及达到收敛所需的训练轮数。此外，ACSP-FL 支持模型个性化，以提升客户端的性能。基于人类活动识别数据集的用例旨在展示 ACSP-FL 相较于现有先进方法的影响与优势。实验评估表明，ACSP-FL 最小化了训练模型所需的总体通信与计算开销，并使系统高效收敛。具体而言，与文献中的方法相比，ACSP-FL 可将通信量减少高达 95%，同时即使在客户端设备间数据以非独立同分布方式分布的场景下，也能提供良好的收敛性。