提出一种通信高效且可调隐私的联邦学习机制，兼顾效率与数据安全。
Communication-Efficient and Privacy-Adaptable Mechanism -- a Federated Learning Scheme with Convergence Analysis
- 使用可调节噪声的随机量化器实现隐私与通信效率平衡。
- 理论证明该机制在不同隐私设置下仍能收敛，实验验证其有效性。
- 适合关注隐私保护与低通信开销的工业级联邦学习应用。
联邦学习允许多方在不共享原始数据的前提下联合训练模型，为数据治理约束下的隐私保护协作提供了可行路径。持续研究联邦学习对解决其关键挑战——通信效率与隐私保护至关重要。近期工作提出一种名为通信高效且可调隐私机制（CEPAM）的新方法，可同时实现上述目标。CEPAM采用拒绝采样的通用量化器（RSUQ），这是一种随机向量量化器，其量化误差等效于预设噪声，且噪声水平可调以定制各方间的隐私保护强度。本文对该机制的隐私保障与收敛性进行了理论分析，并通过实验评估其性能，包括与多种基线方法的收敛曲线对比，以及不同参与方之间的准确率-隐私权衡表现。
原文摘要 · Abstract (English)
Federated learning enables multiple parties to jointly train learning models without sharing their own underlying data, offering a practical pathway to privacy-preserving collaboration under data-governance constraints. Continued study of federated learning is essential to address key challenges in it, including communication efficiency and privacy protection between parties. A recent line of work introduced a novel approach called the Communication-Efficient and Privacy-Adaptable Mechanism (CEPAM), which achieves both objectives simultaneously. CEPAM leverages the rejection-sampled universal quantizer (RSUQ), a randomized vector quantizer whose quantization error is equivalent to a prescribed noise, which can be tuned to customize privacy protection between parties. In this work, we theoretically analyze the privacy guarantees and convergence properties of CEPAM. Moreover, we assess CEPAM's utility performance through experimental evaluations, including convergence profiles compared with other baselines, and accuracy-privacy trade-offs between different parties.
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。