English(EN) ERIS: Enhancing the Privacy-Utility-Scalability Trade-Off in Federated Learning via Federated Shard Aggregation

ERIS框架增强联邦学习的隐私和可扩展性

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-12 04:00

研究人员推出了一种新的联邦学习框架ERIS，旨在改善隐私、效用和可扩展性之间的平衡。ERIS利用联邦分片聚合（FSA）来划分客户端更新，将聚合分布在多个客户端聚合器上。这种方法消除了中央聚合瓶颈，并限制了信息暴露给任何单一观察者。实验表明，ERIS在实现与FedAvg相当的效用的同时，显著降低了通信开销，增强了对隐私攻击的鲁棒性，且无需复杂的密码学。 AI

影响该框架可能能够实现更大规模、更私密的模型训练，尤其是在处理敏感数据的场景下。

排序理由该集群描述了一篇详细介绍一种新颖联邦学习框架的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 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: 10 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群描述了一篇详细介绍一种新颖联邦学习框架的研究论文。[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, 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: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Dario Fenoglio, Pasquale Polverino, Akash Dhasade, Jacopo Quizi, Martin Gjoreski, Marc Langheinrich · 2026-10-12 04:00

ERIS：通过联邦分片聚合增强联邦学习中的隐私-效用-可扩展性权衡

arXiv:2602.08617v3 Announce Type: replace Abstract: Scaling Federated Learning (FL) to billion-parameter models forces a challenging trade-off between privacy, scalability, and model utility. Existing solutions often tackle these challenges in isolation, sacrificing accuracy, rel…

本文如何被排名

报道来源 [1]

ERIS：通过联邦分片聚合增强联邦学习中的隐私-效用-可扩展性权衡

相关实体

相关话题