用预训练模型捕捉全局特征统计，实现一次通信完成联邦学习。
Capture Global Feature Statistics for One-Shot Federated Learning
- 通过预训练模型提取全局特征统计，无需训练即可建模
- 单轮通信下在非独立同分布数据上仍保持稳定性能
- 适合隐私敏感场景，且支持客户端个性化微调
传统联邦学习需多轮通信，导致通信开销大、连接中断风险高且易受隐私攻击。单次通信联邦学习（One-shot FL）可缓解此问题，但现有方法在服务器或客户端计算成本高，且难以有效应对非独立同分布（non-IID）数据。本文提出FedCGS，利用预训练模型捕获全局特征统计，实现无需训练、抗异质性的单轮联邦学习。进一步扩展至个性化场景，客户端仅需额外一轮通信即可下载全局统计信息。大量实验表明，该方法在多种数据异构设置下均表现优异。代码已开源：https://github.com/Yuqin-G/FedCGS。
原文摘要 · Abstract (English)
Traditional Federated Learning (FL) necessitates numerous rounds of communication between the server and clients, posing significant challenges including high communication costs, connection drop risks and susceptibility to privacy attacks. One-shot FL has become a compelling learning paradigm to overcome above drawbacks by enabling the training of a global server model via a single communication round. However, existing one-shot FL methods suffer from expensive computation cost on the server or clients and cannot deal with non-IID (Independent and Identically Distributed) data stably and effectively. To address these challenges, this paper proposes FedCGS, a novel Federated learning algorithm that Capture Global feature Statistics leveraging pre-trained models. With global feature statistics, we achieve training-free and heterogeneity-resistant one-shot FL. Furthermore, we extend its application to personalization scenario, where clients only need execute one extra communication round with server to download global statistics. Extensive experimental results demonstrate the effectiveness of our methods across diverse data heterogeneity settings. Code is available at https://github.com/Yuqin-G/FedCGS.
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。