paper-with-me

홈 › Papers

FedUNet: A Lightweight Additive U-Net Module for Federated Learning with Heterogeneous Models

2025-08-18 · Beomseok Seo, Kichang Lee, JaeYeon Park arxiv

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.

📄 PDF Abstract BibTeX arXiv:2508.12740

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Similar Papers 제목 키워드 기반

MH-pFLID: Model Heterogeneous personalized Federated Learning via Injection and Distillation for Medical Data Analysis

2024-05-10 · Luyuan Xie, Manqing Lin, Tianyu Luan, Cong Li 외

Federated learning is widely used in medical applications for training global models without needing local data access. However, varying computational capabilities and network architectures (system heterogeneity), across…

Federated LearningKnowledge DistillationPersonalized Federated Learning

Practical and Private Heterogeneous Federated Learning

2021-09-29 · Hanxiao Chen, Meng Hao, Hongwei Li, Guangxiao Niu 외

Heterogeneous federated learning (HFL) enables clients with different computation/communication capabilities to collaboratively train their own customized models, in which the knowledge of models is shared via clients' p…

Federated LearningPrivacy Preserving

Personalized Federated Fine-Tuning for LLMs via Data-Driven Heterogeneous Model Architectures

2024-11-28 · YiCheng Zhang, Zhen Qin, Zhaomin Wu, Shuiguang Deng

A large amount of instructional text data is essential to enhance the performance of pre-trained large language models (LLMs) for downstream tasks. This data can contain sensitive information and therefore cannot be shar…

Federated Learning

Federated Learning for Inference at Anytime and Anywhere

2022-12-08 · Zicheng Liu, Da Li, Javier Fernandez-Marques, Stefanos Laskaridis 외

Federated learning has been predominantly concerned with collaborative training of deep networks from scratch, and especially the many challenges that arise, such as communication cost, robustness to heterogeneous data, …

Federated Learning

Leveraging Foundation Models to Improve Lightweight Clients in Federated Learning

2023-11-14 · Xidong Wu, Wan-Yi Lin, Devin Willmott, Filipe Condessa 외

Federated Learning (FL) is a distributed training paradigm that enables clients scattered across the world to cooperatively learn a global model without divulging confidential data. However, FL faces a significant challe…

Federated Learning