用基础模型指导联邦学习聚合，保护隐私同时提升精度
FedBaF: Federated Learning Aggregation Biased by a Foundation Model
- 在联邦聚合阶段动态引入基础模型权重，不暴露原始模型
- 非独立同分布场景下准确率提升15.8%，语言模型困惑度降39.2%
- 适合注重数据安全与跨客户端性能优化的研究者
基础模型因强大的泛化能力成为技术巨头关注焦点。现有方法在适配新应用时依赖联邦学习，并将基础模型权重披露给客户端以初始化全局模型，虽保障客户端数据隐私，却损害模型与信息安全性。本文提出联邦学习聚合中受基础模型引导的方法（FedBaF），在聚合阶段动态融合预训练基础模型权重。该方法在不泄露基础模型的前提下，显著提升模型精度，尤其在非独立同分布（non-IID）及对抗性场景中表现优异。实验采用Pre-ResNet与Vision Transformer等基础模型，在非IID设置下测试准确率最高提升15.8%，在独立同分布（IID）下提升11.4%；应用于基于Transformer的语言模型时，困惑度最高降低39.2%。
原文摘要 · Abstract (English)
Foundation models are now a major focus of leading technology organizations due to their ability to generalize across diverse tasks. Existing approaches for adapting foundation models to new applications often rely on Federated Learning (FL) and disclose the foundation model weights to clients when using it to initialize the global model. While these methods ensure client data privacy, they compromise model and information security. In this paper, we introduce Federated Learning Aggregation Biased by a Foundation Model (FedBaF), a novel method for dynamically integrating pre-trained foundation model weights during the FL aggregation phase. Unlike conventional methods, FedBaF preserves the confidentiality of the foundation model while still leveraging its power to train more accurate models, especially in non-IID and adversarial scenarios. Our comprehensive experiments use Pre-ResNet and foundation models like Vision Transformer to demonstrate that FedBaF not only matches, but often surpasses the test accuracy of traditional weight initialization methods by up to 11.4% in IID and up to 15.8% in non-IID settings. Additionally, FedBaF applied to a Transformer-based language model significantly reduced perplexity by up to 39.2%.
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。