cs.AI updates on arXiv.org 10小时前
FedUNet: A Lightweight Additive U-Net Module for Federated Learning with Heterogeneous Models
index_new5.html
../../../zaker_core/zaker_tpl_static/wap/tpl_guoji1.html

 

本文提出FedUNet,一种轻量级且架构无关的联邦学习框架,通过添加U-Net模块实现高效知识转移,实现93.11%准确率,通信开销仅0.89MB。

arXiv:2508.12740v1 Announce Type: cross Abstract: Federated learning (FL) enables decentralized model training without sharing local data. However, most existing methods assume identical model architectures across clients, limiting their applicability in heterogeneous real-world environments. To address this, we propose FedUNet, a lightweight and architecture-agnostic FL framework that attaches a U-Net-inspired additive module to each client's backbone. By sharing only the compact bottleneck of the U-Net, FedUNet enables efficient knowledge transfer without structural alignment. The encoder-decoder design and skip connections in the U-Net help capture both low-level and high-level features, facilitating the extraction of clientinvariant representations. This enables cooperative learning between the backbone and the additive module with minimal communication cost. Experiment with VGG variants shows that FedUNet achieves 93.11% accuracy and 92.68% in compact form (i.e., a lightweight version of FedUNet) with only 0.89 MB low communication overhead.

Fish AI Reader

Fish AI Reader

AI辅助创作,多种专业模板,深度分析,高质量内容生成。从观点提取到深度思考,FishAI为您提供全方位的创作支持。新版本引入自定义参数,让您的创作更加个性化和精准。

FishAI

FishAI

鱼阅,AI 时代的下一个智能信息助手,助你摆脱信息焦虑

联系邮箱 441953276@qq.com

相关标签

联邦学习 FedUNet U-Net 模型训练 知识迁移
相关文章