English(EN) FedSumUp: User-Auditable Privacy-Aware Representation Sharing for Resource-Constrained Federated Intelligence

新的FedSumUp方法增强了联邦学习的隐私和效率

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-16 04:00

研究人员开发了FedSumUp，一种新颖的联邦学习方法，可增强隐私并减少客户端设备的计算开销。FedSumUp利用可学习的有损压缩器生成紧凑、可解释的表示，允许用户直接评估隐私-效用权衡。这种方法最大限度地减少了隐私泄露，同时保留了任务相关的语义，并在BloodMNIST、CIFAR-10和ChestMNIST等数据集上展示了客户端运行时间高达96.5%的显著缩减，同时保持了具有竞争力的分类准确性。 AI

影响提高了资源受限设备上联邦学习的隐私和效率。

排序理由该集群包含一篇详细介绍联邦学习新方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 22 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍联邦学习新方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, safety, infra; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Jingwei Zhao, Tiantong Sun, Yuanyuan Song, Jinhuan Guo, Wei Zishuo, Shengyu Huang, Ziyuan Ren, Wei Chen, Xiaojin Zhang · 2026-10-16 04:00

FedSumUp：面向资源受限联邦智能的、用户可审计的隐私感知表示共享

arXiv:2610.21194v1 Announce Type: cross Abstract: Existing federated data condensation methods face privacy risks, as uploaded synthetic data may preserve sensitive information and remain vulnerable to reconstruction attacks. Moreover, their generation often incurs considerable c…

本文如何被排名

报道来源 [1]

FedSumUp：面向资源受限联邦智能的、用户可审计的隐私感知表示共享

相关实体

相关话题