English(EN) Machine Unlearning for Class Removal through SISA-based Deep Neural Network Architectures

新的SISA框架实现了CNN中高效的类别级机器遗忘

作者 PulseAugur 编辑部 · [2 个来源] · 2026-04-30 12:47

研究人员开发了一种新颖的机器遗忘技术，专门用于从深度神经网络中移除整个数据类别。该方法修改了分片、隔离、切片和聚合（SISA）框架，并结合了强化回放机制和门控网络来改进选择性遗忘。实验表明，该方法可以有效地从卷积神经网络中移除数据类别，同时保持模型的整体性能并减少完全重新训练的需要。 AI

影响通过允许在不完全重新训练的情况下进行有针对性的类别移除，从而实现更高效的AI模型数据隐私合规性。

排序理由关于用于类别移除的新型机器遗忘技术的学术论文。

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.CV TIER_1 English(EN) · Ishrak Hamim Mahi, Siam Ferdous, Md Sakib Sadman Badhon, Nabid Hasan Omi, Md Habibun Nabi Hemel, Farig Yousuf Sadeque, Md. Tanzim Reza · 2026-05-01 04:00

Machine Unlearning for Class Removal through SISA-based Deep Neural Network Architectures

arXiv:2604.27804v1 Announce Type: new Abstract: The rapid proliferation of image generation models and other artificial intelligence (AI) systems has intensified concerns regarding data privacy and user consent. As the availability of public datasets declines, major technology co…
arXiv cs.CV TIER_1 English(EN) · Md. Tanzim Reza · 2026-04-30 12:47

Machine Unlearning for Class Removal through SISA-based Deep Neural Network Architectures

The rapid proliferation of image generation models and other artificial intelligence (AI) systems has intensified concerns regarding data privacy and user consent. As the availability of public datasets declines, major technology companies increasingly rely on proprietary or priv…