paper-with-me

홈 › Papers

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

2025-04-20 · Shunxin Guo, Jiaqi Lv, Qiufeng Wang, Xin Geng

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.

📄 PDF Abstract BibTeX arXiv:2504.14628

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Similar Papers 제목 키워드 기반

FedEU: Evidential Uncertainty-Driven Federated Fine-Tuning of Vision Foundation Models for Remote Sensing Image Segmentation

2026-03-08 · Xiaokang Zhang, Xuran Xiong, Jianzhong Huang, Lefei Zhang arxiv

Remote sensing image segmentation (RSIS) in federated environments has gained increasing attention because it enables collaborative model training across distributed datasets without sharing raw imagery or annotations. F…

parameter-efficient fine-tuningImage Segmentation

Federated Nonlinear System Identification

2025-08-20 · Omkar Tupe, Max Hartman, Lav R. Varshney, Saurav Prakash arxiv

We consider federated learning of linearly-parameterized nonlinear systems. We establish theoretical guarantees on the effectiveness of federated nonlinear system identification compared to centralized approaches, demons…

Federated Learning

Adaptive Federated Learning via Dynamical System Model

2025-10-05 · Aayushya Agarwal, Larry Pileggi, Gauri Joshi arxiv

Hyperparameter selection is critical for stable and efficient convergence of heterogeneous federated learning, where clients differ in computational capabilities, and data distributions are non-IID. Tuning hyperparameter…

Federated Learning

Dynamic Fair Federated Learning Based on Reinforcement Learning

2023-11-02 · Weikang Chen, Junping Du, Yingxia Shao, Jia Wang 외

Federated learning enables a collaborative training and optimization of global models among a group of devices without sharing local data samples. However, the heterogeneity of data in federated learning can lead to unfa…

FairnessFederated Learningreinforcement-learningReinforcement Learning

Channel-driven Decentralized Bayesian Federated Learning for Trustworthy Decision Making in D2D Networks

2022-10-19 · Luca Barbieri, Osvaldo Simeone, Monica Nicoli

Bayesian Federated Learning (FL) offers a principled framework to account for the uncertainty caused by limitations in the data available at the nodes implementing collaborative training. In Bayesian FL, nodes exchange i…

Decision MakingFederated Learning