PulseAugur
实时 21:31:01
English(EN) Enhanced Privacy and Communication Efficiency in Non-IID Federated Learning with Adaptive Quantization and Differential Privacy

联邦学习进展在隐私、效用和公平性之间取得平衡

研究人员正在探索增强联邦学习(FL)隐私的高级技术,FL是一种在去中心化数据上进行模型训练的方法。一项研究比较了在瑞典医疗保健数据上用于心血管疾病风险建模的差分隐私(DP)和同态加密(HE),发现HE与集中式方法相当,但计算开销更高,而DP在某些模型上表现出更大的性能下降。另一种方法FedPF引入了一种差分隐私的公平FL算法,通过将公平性和效用视为竞争目标来平衡它们,在具有竞争力的准确性和低计算占用的情况下显著减少了歧视。第三篇论文将DP与自适应量化相结合,以提高非独立同分布(non-IID)FL设置中的通信效率和隐私,在保持准确性和强大隐私的同时,在图像数据集上实现了大量数据缩减。 AI

影响 隐私保护联邦学习的进步可能在医疗保健和边缘计算等敏感领域实现更安全、更高效的协作人工智能开发。

排序理由 多篇arXiv论文详细介绍了隐私保护联邦学习技术的新研究。

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 4 个来源。 我们如何撰写摘要 →

联邦学习进展在隐私、效用和公平性之间取得平衡

报道来源 [4]

  1. arXiv cs.LG TIER_1 English(EN) · Gaurang Sharma, Juha Pajula, Aada Illikainen, Markus Rautell, Noora Lipsonen, Petri Alhainen, Mika Hilvo ·

    通过差分隐私和同态加密实现保护隐私的联邦学习用于心血管疾病风险建模

    arXiv:2604.27598v1 Announce Type: new Abstract: Protecting sensitive health data while enabling collaborative analysis is a central challenge in healthcare. Traditional machine learning (ML) requires institutions to pool anonymized patient records, centralizing analytical develop…

  2. arXiv cs.LG TIER_1 English(EN) · Mika Hilvo ·

    通过差分隐私和同态加密实现保护隐私的联邦学习,用于心血管疾病风险建模

    Protecting sensitive health data while enabling collaborative analysis is a central challenge in healthcare. Traditional machine learning (ML) requires institutions to pool anonymized patient records, centralizing analytical development and privacy risks at a single site. Privacy…

  3. arXiv cs.AI TIER_1 English(EN) · Kangkang Sun, Jun Wu, Minyi Guo, Jianhua Li, Jianwei Huang ·

    FedPF:平衡公平性和效用的准确目标隐私保护联邦学习

    arXiv:2510.26841v2 Announce Type: replace-cross Abstract: Federated Learning (FL) enables collaborative model training without data sharing, yet participants face a fundamental challenge, e.g., simultaneously ensuring fairness across demographic groups while protecting sensitive …

  4. arXiv cs.CV TIER_1 English(EN) · Emre Ard{\i}\c{c}, Yakup Gen\c{c} ·

    基于自适应量化和差分隐私的非独立同分布联邦学习中的增强隐私与通信效率

    arXiv:2604.23426v1 Announce Type: new Abstract: Federated learning (FL) is a distributed machine learning method where multiple devices collaboratively train a model under the management of a central server without sharing underlying data. One of the key challenges of FL is the c…