首次发布 Vision Transformers 的机器遗忘基准测试

作者 PulseAugur 编辑部 · [1 个来源] · 2026-07-24 04:00

一篇新的研究论文介绍了首个专门为 Vision Transformers (VTs) 设计的机器遗忘 (MU) 基准测试。该研究弥补了 MU 研究的空白，因为该领域的研究主要集中在卷积神经网络 (CNNs) 上，而不是计算机视觉中日益流行的 VTs。该基准测试采用了各种数据集、MU 算法和协议，为比较 VTs 上 MU 算法的性能提供了一种标准化且可复现的方法，为未来的研究奠定了参考基线。 AI

影响为评估 Vision Transformers 上的机器遗忘技术建立了标准化基准，这对于 AI 安全和公平至关重要。

排序理由该集群包含一篇介绍 Vision Transformers 机器遗忘新基准的研究论文。[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: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇介绍 Vision Transformers 机器遗忘新基准的研究论文。[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, 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: 60 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.AI TIER_1 English(EN) · Kairan Zhao, Iurie Luca, Peter Triantafillou · 2026-07-24 04:00

Vision Transformers 的遗忘基准测试

arXiv:2602.20114v2 Announce Type: replace-cross Abstract: Machine unlearning (MU) refers to the post-training capability to remove (the influence of) training examples that are incorrect, biased, or leak sensitive/private information. MU is now widely regarded as critical for bui…

本文如何被排名

报道来源 [1]

Vision Transformers 的遗忘基准测试

相关实体

相关话题