Reproducible Implementation of an Attention-Enhanced Meta-Learning Network for Personalized Federated Learning with Heterogeneous Client Data
Journal of Visualized Experiments · 2026-11-03 · (237)
DOI: 10.3791/73463 ↗At a glance
Video/Audio in Journal of Visualized Experiments, published online on 2026-11-03. Written by Wei Gao and 3 co-authors. Institution: School of Computer Science and Data Engineering, NingboTech University; gw_nbt@163.com. Major MEDLINE topics: Federated Learning, Image Processing, Computer-Assisted.
Abstract (original language)
This protocol describes the implementation and evaluation of attention-enhanced meta-learning personalized federated learning (AEML-PFL) for heterogeneous image-classification clients. The custom PyTorch simulation uses 50 clients, synchronous aggregation, and five independent random-seed runs. It evaluates Fashion-MNIST, Federated Extended MNIST (FEMNIST), and the Canadian Institute for Advanced Research datasets CIFAR-10 and CIFAR-100. Client data are not independent and identically distributed (non-IID). FEMNIST uses the same 50-writer cohort of 18,642 images across all five seeds; the other datasets use Dirichlet-based label partitions. Personalized test accuracies are 93.6%, 86.0%, 74.3%, and 47.1%, respectively, after checkpoint selection by validation accuracy. On CIFAR-10, the mean accuracy of the five worst-performing clients is 62.7%, and the across-client standard deviation is 6.2 percentage points. The number of rounds to 95% of each method's own peak validation accuracy is 166 for AEML-PFL and 214 for federated averaging. The protocol provides a workflow for examining personalized performance under label and sample-count heterogeneity.
Subjects
MeSH terms (MEDLINE)
Authors and institutions
- School of Computer Science and Data Engineering, NingboTech University; gw_nbt@163.com.
- School of Computer Science and Data Engineering, NingboTech University.
Cite
APA
Gao, W., Xiao, H., Yu, X., & Yu, X. (2026). Reproducible Implementation of an Attention-Enhanced Meta-Learning Network for Personalized Federated Learning with Heterogeneous Client Data. Journal of Visualized Experiments. https://doi.org/10.3791/73463
Vancouver
Gao W, Xiao H, Yu X, Yu X. Reproducible Implementation of an Attention-Enhanced Meta-Learning Network for Personalized Federated Learning with Heterogeneous Client Data. Journal of Visualized Experiments. 2026. doi:10.3791/73463
BibTeX
@article{Gao2026,
author = {Gao, Wei and Xiao, Hui and Yu, Xinjie and Yu, Xin},
title = {Reproducible Implementation of an Attention-Enhanced Meta-Learning Network for Personalized Federated Learning with Heterogeneous Client Data},
journal = {Journal of Visualized Experiments},
year = {2026},
number = {237},
doi = {10.3791/73463}
}
EUVIMED