GENE-FL: Gene-Driven Parameter-Efficient Dynamic Federated Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Guo, Shunxin, Lv, Jiaqi, Wang, Qiufeng, Geng, Xin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908328713519104
author Guo, Shunxin
Lv, Jiaqi
Wang, Qiufeng
Geng, Xin
author_facet Guo, Shunxin
Lv, Jiaqi
Wang, Qiufeng
Geng, Xin
contents Real-world \underline{F}ederated \underline{L}earning systems often encounter \underline{D}ynamic clients with \underline{A}gnostic and highly heterogeneous data distributions (DAFL), which pose challenges for efficient communication and model initialization. To address these challenges, we draw inspiration from the recently proposed Learngene paradigm, which compresses the large-scale model into lightweight, cross-task meta-information fragments. Learngene effectively encapsulates and communicates core knowledge, making it particularly well-suited for DAFL, where dynamic client participation requires communication efficiency and rapid adaptation to new data distributions. Based on this insight, we propose a Gene-driven parameter-efficient dynamic Federated Learning (GENE-FL) framework. First, local models perform quadratic constraints based on parameters with high Fisher values in the global model, as these parameters are considered to encapsulate generalizable knowledge. Second, we apply the strategy of parameter sensitivity analysis in local model parameters to condense the \textit{learnGene} for interaction. Finally, the server aggregates these small-scale trained \textit{learnGene}s into a robust \textit{learnGene} with cross-task generalization capability, facilitating the rapid initialization of dynamic agnostic client models. Extensive experimental results demonstrate that GENE-FL reduces \textbf{4 $\times$} communication costs compared to FEDAVG and effectively initializes agnostic client models with only about \textbf{9.04} MB.
format Preprint
id arxiv_https___arxiv_org_abs_2504_14628
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GENE-FL: Gene-Driven Parameter-Efficient Dynamic Federated Learning
Guo, Shunxin
Lv, Jiaqi
Wang, Qiufeng
Geng, Xin
Distributed, Parallel, and Cluster Computing
Machine Learning
Real-world \underline{F}ederated \underline{L}earning systems often encounter \underline{D}ynamic clients with \underline{A}gnostic and highly heterogeneous data distributions (DAFL), which pose challenges for efficient communication and model initialization. To address these challenges, we draw inspiration from the recently proposed Learngene paradigm, which compresses the large-scale model into lightweight, cross-task meta-information fragments. Learngene effectively encapsulates and communicates core knowledge, making it particularly well-suited for DAFL, where dynamic client participation requires communication efficiency and rapid adaptation to new data distributions. Based on this insight, we propose a Gene-driven parameter-efficient dynamic Federated Learning (GENE-FL) framework. First, local models perform quadratic constraints based on parameters with high Fisher values in the global model, as these parameters are considered to encapsulate generalizable knowledge. Second, we apply the strategy of parameter sensitivity analysis in local model parameters to condense the \textit{learnGene} for interaction. Finally, the server aggregates these small-scale trained \textit{learnGene}s into a robust \textit{learnGene} with cross-task generalization capability, facilitating the rapid initialization of dynamic agnostic client models. Extensive experimental results demonstrate that GENE-FL reduces \textbf{4 $\times$} communication costs compared to FEDAVG and effectively initializes agnostic client models with only about \textbf{9.04} MB.
title GENE-FL: Gene-Driven Parameter-Efficient Dynamic Federated Learning
topic Distributed, Parallel, and Cluster Computing
Machine Learning
url https://arxiv.org/abs/2504.14628