新的联邦持续遗忘方法可实现对AI模型的精确数据移除

作者 PulseAugur 编辑部 · [1 个来源] · 2026-06-16 04:00

研究人员开发了一种新颖的联邦持续遗忘方法，该方法专门针对具有冻结基础模型和可训练脊回归头部的模型。这种方法允许按需精确移除模型中特定数据的 the influence，解决了联邦学习设置中的“被遗忘权”要求。该方法利用一种通信协议，通过固定大小的消息有效地更新模型头部，确保服务器的模型始终与集中式再训练相同，即使有连续的添加和删除请求。在四个基准上的实验表明，该技术实现了近乎完美的准确性，以最小的 Frobenius 误差匹配集中式再训练，同时与传统的联邦再训练相比显著降低了计算成本。 AI

影响在联邦学习中实现精确数据移除，增强了AI模型的隐私合规性。

排序理由关于联邦持续遗忘新方法的学术论文。[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: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 关于联邦持续遗忘新方法的学术论文。[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, model release, safety; 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: 114 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Yijun Quan, Wentai Wu, Giovanni Montana · 2026-06-16 04:00

面向冻结基础模型的脊头精确联邦持续遗忘

arXiv:2603.12977v3 Announce Type: replace Abstract: Foundation models are commonly deployed as frozen feature extractors with a small trainable head to adapt to private, user-generated data in federated settings. The ``right to be forgotten'' requires removing the influence of sp…

本文如何被排名

报道来源 [1]

面向冻结基础模型的脊头精确联邦持续遗忘

相关实体

相关话题