Computer Science Faculty Publications
Document Type
Article
Publication Date
12-2025
Abstract
Federated learning (FL) using the federated averaging (FedAvg) algorithm has shown great advantages for large-scale applications that rely on collaborative learning, especially when the training data is either unbalanced or inaccessible due to privacy constraints. We hypothesize that FedAvg underestimates the full extent of heterogeneity of data when the aggregation is performed. We propose Precision-Weighted Federated Learning (PW) a novel algorithm that takes into account the second raw moment (uncentered variance) of the stochastic gradient when computing the weighted average of the parameters of independent models trained in a FL setting. With PW, we address the communication and statistical challenges for the training of distributed models with private data and provide an alternate averaging scheme that leverages the heterogeneity of the data when it has a large diversity of features in its composition. Our method was evaluated using three standard image classification datasets (MNIST, Fashion-MNIST, and CIFAR) under two different data partitioning strategies: independent and identically distributed (IID), and nonidentical and nonindependent (non-IID). These experiments were designed to measure the performance and efficiency of our method in resource-constrained environments, such as mobile and IoT devices. The experimental results demonstrate that we can obtain a good balance between computational efficiency and convergence rates with PW. Our performance evaluations show better predictions with MNIST, with Fashion-MNIST, and with CIFAR-10 in the non-IID setting. Further reliability evaluations ratify the stability in our method by reaching a 99% reliability index with IID partitions and 96% with non-IID partitions. In addition, we obtained a speedup on Fashion-MNIST with only 10 clients and up to with 100 clients participating in the aggregation concurrently per communication round. Overall, PW demonstrates improved stability and accuracy with increasing batch sizes, and it benefits significantly from lower learning rates and longer local training, compared to FedAvg and FedProx. The results indicate that PW is an effective and faster alternative approach for aggregating model updates derived from private data, especially in domains where data is highly heterogeneous.
Recommended Citation
Reyes, Jonatan, Lisa Di Jorio, Cecile Low‐Kam, and Marta Kersten‐Oertel. "Precision‐Weighted Federated Learning." Computational Intelligence 41, no. 6 (2025): e70150. https://doi.org/10.1111/coin.70150
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
Publication Title
Computational Intelligence
DOI
10.1111/coin.70150
Comments
© 2025 The Author(s). Computational Intelligence published by Wiley Periodicals LLC.
This is an open access article under the terms of the Creative Commons Attribution-NonCommercial License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited and is not used for commercial purposes.