01291nas a2200169   4500000000100000008004100001260006000042100001800102700001100120700001800131700001800149700001600167245007200183856004900255520079500304020002201099       2023                            d  c08/2023bSpringer International PublishingaCusco, Peru1 aFelix Freitag1 aLu Wei1 aChun-Hung Liu1 aMennan Selimi1 aLuís Veiga00aServer-side Adaptive Federated Learning over Wireless Mesh Network  uhttps://doi.org/10.1007/978-3-031-33261-6_253 aIn federated learning, distributed nodes train a local machine learning model and exchange it through a central aggregator. In real environments, these training nodes are heterogeneous in computing capacity and bandwidth, thus their specific characteristics influence the performance of the federated learning process. We propose for such situations the design of a federated learning server that is able to adapt dynamically to the heterogeneity of the training nodes. In experiments with real devices deployed in a wireless mesh network, we observed that the designed adaptive federated learning server successfully exploited the idle times of the fast nodes by assigning them larger training workloads, which led to a higher global model performance without increasing the training time.  a978-3-031-33261-6