用编码增强聚合，让分层联邦学习在不稳网络下更安全、准确、高效。
Coding-Enforced Resilient and Secure Aggregation for Hierarchical Federated Learning
- 引入编码策略强制聚合结构，解决隐私噪声干扰问题。
- 在任意强隐私保护下仍能准确构建全局模型，避免部分参与缺陷。
- 适合对通信可靠性与隐私要求高的实际部署场景。
分层联邦学习（HFL）已成为提升客户端与服务器间链路质量的有效范式。然而，在不可靠通信条件下，如何在保障隐私的同时维持模型精度仍是关键挑战，因隐私噪声的协调可能被随机破坏。为解决此问题，本文提出一种鲁棒的分层安全聚合方案 H-SecCoGC，通过集成编码策略实现结构化聚合。该方案不仅在不同隐私级别下确保全局模型的准确构建，还避免了部分参与问题，显著提升鲁棒性、隐私保护能力和学习效率。理论分析与实验结果均表明，本方案在任意强隐私保证下的不可靠通信环境中表现优异。
原文摘要 · Abstract (English)
Hierarchical federated learning (HFL) has emerged as an effective paradigm to enhance link quality between clients and the server. However, ensuring model accuracy while preserving privacy under unreliable communication remains a key challenge in HFL, as the coordination among privacy noise can be randomly disrupted. To address this limitation, we propose a robust hierarchical secure aggregation scheme, termed H-SecCoGC, which integrates coding strategies to enforce structured aggregation. The proposed scheme not only ensures accurate global model construction under varying levels of privacy, but also avoids the partial participation issue, thereby significantly improving robustness, privacy preservation, and learning efficiency. Both theoretical analyses and experimental results demonstrate the superiority of our scheme under unreliable communication across arbitrarily strong privacy guarantees
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。