FedUNet让不同模型的客户端也能高效协作训练。
FedUNet: A Lightweight Additive U-Net Module for Federated Learning with Heterogeneous Models
- 在各客户端模型不一致时，加一个轻量U-Net模块实现知识共享。
- 仅传0.89MB瓶颈信息，准确率最高达93.11%。
- 适合模型异构的现实场景，通信开销极低。
联邦学习（FL）可在不共享本地数据的前提下实现分布式模型训练。然而，现有方法大多假设客户端模型结构相同，难以适应真实世界中模型异构的环境。为此，我们提出FedUNet，一种轻量级且架构无关的联邦学习框架。该框架在每个客户端的主干网络上附加一个受U-Net启发的可添加模块，通过仅共享模块的紧凑瓶颈部分，实现高效的知识迁移而无需结构对齐。U-Net的编码器-解码器结构与跳跃连接有助于捕捉低层和高层特征，促进提取客户端不变表示。这使得主干网络与附加模块之间能以最小通信成本进行协同学习。使用VGG变体的实验表明，FedUNet在完整形式下达到93.11%准确率，在紧凑形式下达到92.68%，通信开销仅为0.89 MB。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。