English(EN) Machine Unlearning in Low-Dimensional Feature Subspace

新的LOFT方法可在低维特征子空间中实现高效的机器遗忘

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-22 04:00

研究人员推出了一种新颖的机器遗忘方法LOFT，该方法在低维特征子空间中运行。该方法旨在从预训练模型中移除特定数据的影，同时保留模型在剩余数据上的性能。LOFT通过优化一个小的投影矩阵来实现这一点，仅需从预训练模型中进行一次特征提取即可，从而显著降低了计算开销，并在各种模型和数据集上展现出优越的遗忘性能。 AI

影响这项研究可能为AI系统中数据隐私和模型管理带来更高效、计算成本更低的方法。

排序理由该集群包含一篇详细介绍机器遗忘新方法的论文。[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: 1 / 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机器遗忘新方法的论文。[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, model release; 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: 1 days old; Coverage has settled into its steady-state 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) · Kun Fang, Qinghua Tao, Junxu Liu, Yaxin Xiao, Yulin Jin, Qingqing Ye, Jian Sun, Haibo Hu · 2026-10-22 04:00

低维特征子空间中的机器遗忘

arXiv:2601.22456v3 Announce Type: replace Abstract: Machine Unlearning (MU) aims at removing the influence of specific data from a pretrained model while preserving performance on the remaining data. In this work, a novel perspective for MU is presented upon low-dimensional featu…

本文如何被排名

报道来源 [1]

低维特征子空间中的机器遗忘

相关实体

相关话题