用生成式AI自动生成验证数据，提前停止联邦学习训练。
When to Stop Federated Learning: Zero-Shot Generation of Synthetic Validation Data with Generative AI for Early Stopping
- 用生成式AI零样本构建合成验证数据，实时监控模型性能。
- 在多标签胸部X光分类任务中减少74%训练轮次，精度损失小于1%。
- 适合需要快速调参、节省算力的联邦学习场景。
联邦学习（FL）可在保护数据隐私的前提下实现分布式设备间的协作模型训练。然而，传统方法通常按预设轮数运行，常导致在模型达到最优前仍继续训练，或在模型无有效性能时持续耗时。为解决该效率问题，本文提出一种零样本合成验证框架，利用生成式AI动态生成验证数据，监测模型表现并确定早期停止点。该方法可自适应地在接近最优轮次时终止训练，显著节约计算资源，并支持快速超参数调整。在多标签胸部X光分类任务上的实验表明，该方法最多可减少74%的训练轮数，同时保持精度在最优值的1%以内。
原文摘要 · Abstract (English)
Federated Learning (FL) enables collaborative model training across decentralized devices while preserving data privacy. However, FL methods typically run for a predefined number of global rounds, often leading to unnecessary computation when optimal performance is reached earlier. In addition, training may continue even when the model fails to achieve meaningful performance. To address this inefficiency, we introduce a zero-shot synthetic validation framework that leverages generative AI to monitor model performance and determine early stopping points. Our approach adaptively stops training near the optimal round, thereby conserving computational resources and enabling rapid hyperparameter adjustments. Numerical results on multi-label chest X-ray classification demonstrate that our method reduces training rounds by up to 74% while maintaining accuracy within 1% of the optimal.
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。