用固定特征提取器+单层学习，实现高效低耗的联邦图像分类。
FedHENet: A Frugal Federated Learning Framework for Heterogeneous Environments
- 固定预训练模型，只训练输出层，避免本地微调开销。
- 单轮通信完成聚合，准确率媲美迭代式联邦学习，能效提升70%。
- 无需超参调优，适合资源受限或对碳足迹敏感的场景。
联邦学习（FL）可在不集中数据的前提下实现协作训练，对涉及敏感视觉信息的真实场景具有重要隐私保护意义。现有大多数FL方法依赖昂贵的迭代深度网络优化，仍存在通过共享梯度泄露隐私的风险。本文提出FedHENet，基于FedHEONN框架扩展至图像分类任务。采用固定预训练特征提取器，仅学习单个输出层，避免高成本的本地微调。该输出层通过同态加密（HE）在单轮通信中解析聚合客户端知识。实验表明，与迭代式FL基线相比，FedHENet在准确率上具有竞争力，同时展现出更优的稳定性及最高达70%的能效提升。关键优势在于无需超参数调优，消除了传统FL中因超参搜索带来的碳足迹。代码已开源：https://github.com/AlejandroDopico2/FedHENet/
原文摘要 · Abstract (English)
Federated Learning (FL) enables collaborative training without centralizing data, essential for privacy compliance in real-world scenarios involving sensitive visual information. Most FL approaches rely on expensive, iterative deep network optimization, which still risks privacy via shared gradients. In this work, we propose FedHENet, extending the FedHEONN framework to image classification. By using a fixed, pre-trained feature extractor and learning only a single output layer, we avoid costly local fine-tuning. This layer is learned by analytically aggregating client knowledge in a single round of communication using homomorphic encryption (HE). Experiments show that FedHENet achieves competitive accuracy compared to iterative FL baselines while demonstrating superior stability performance and up to 70\% better energy efficiency. Crucially, our method is hyperparameter-free, removing the carbon footprint associated with hyperparameter tuning in standard FL. Code available in https://github.com/AlejandroDopico2/FedHENet/
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。