针对通信噪声提升的胚胎图像分割联邦学习方法
Smart Split-Federated Learning over Noisy Channels for Embryo Image Segmentation
- 设计智能平均策略，增强联邦学习在噪声信道中的鲁棒性
- 可容忍比传统方法强100倍的通信噪声，保持模型精度
- 适合边缘设备算力有限且通信环境差的医疗图像任务
Split-Federated（SplitFed）学习是联邦学习的一种扩展，对客户端计算资源要求较低，仅需在客户端部署模型的小部分。在SplitFed中，特征值、梯度更新和模型更新通过通信信道传输。本文研究了通信信道噪声对学习过程及最终模型质量的影响。提出一种针对SplitFed的智能平均策略，旨在提升对信道噪声的抗性。在胚胎图像分割模型上的实验表明，所提智能平均策略可在通信信道噪声强度提高两个数量级的情况下仍保持模型准确率，显著优于传统平均方法。
原文摘要 · Abstract (English)
Split-Federated (SplitFed) learning is an extension of federated learning that places minimal requirements on the clients computing infrastructure, since only a small portion of the overall model is deployed on the clients hardware. In SplitFed learning, feature values, gradient updates, and model updates are transferred across communication channels. In this paper, we study the effects of noise in the communication channels on the learning process and the quality of the final model. We propose a smart averaging strategy for SplitFed learning with the goal of improving resilience against channel noise. Experiments on a segmentation model for embryo images shows that the proposed smart averaging strategy is able to tolerate two orders of magnitude stronger noise in the communication channels compared to conventional averaging, while still maintaining the accuracy of the final model.
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。