研究人员开发了新的方法来增强联邦学习中的隐私和效率。一种方法侧重于通过使用 Top-K 梯度稀疏化来降低通信成本，该方法仅传输必要的梯度信息，同时保持模型准确性。另一个框架 DDP-SA 将本地差分隐私与秘密共享相结合，以确保没有任何单个服务器可以访问单个客户端数据，从而提供比现有方法更强的隐私保证。这些进展旨在使联邦学习更具可扩展性和安全性，特别是对于大型模型和去中心化系统。 AI
影响 这些方法旨在使联邦学习在大型人工智能模型训练中更实用、更安全。
排序理由 多篇学术论文提出了联邦学习的新技术。
AI 生成摘要 · Google Gemini · 来自 5 个来源。 我们如何撰写摘要 →
arXiv:2606.10780v1 Announce Type: cross Abstract: Secure aggregation is a vital component for mitigating gradient leakage in federated learning, but its communication cost conventionally scales with the gradient dimension. This becomes prohibitive for large models and even more p…
Secure aggregation is a vital component for mitigating gradient leakage in federated learning, but its communication cost conventionally scales with the gradient dimension. This becomes prohibitive for large models and even more pronounced in decentralized federated learning with…
arXiv:2604.07125v2 Announce Type: replace-cross Abstract: This article presents DDP-SA, a scalable privacy-preserving federated learning framework that jointly leverages client-side local differential privacy (LDP) and full-threshold additive secret sharing (ASS) for secure aggre…
arXiv:2606.07277v1 Announce Type: cross Abstract: Secure aggregation allows a server to aggregate users' local updates while preserving update privacy. Existing information-theoretic problems typically assume that correlated random keys are provided by a trusted third party (TTP)…
Secure aggregation allows a server to aggregate users' local updates while preserving update privacy. Existing information-theoretic problems typically assume that correlated random keys are provided by a trusted third party (TTP) or generated via prescribed groupwise structures,…