两篇新研究论文提出了机器学习遗忘的新颖方法，这是一个从训练模型中移除特定数据影响的过程。第一篇论文《有多难？硬度感知多目标遗忘》介绍了HAMU，它根据数据相似性量化遗忘的难度，并保证在最小化效用损失的同时，遗忘质量得到指定程度的提升。第二篇论文《多目标参考对齐机器学习遗忘》提出了RAUL框架，该框架将遗忘样本的预测与参考分布对齐，以约束遗忘并减少与保留的冲突，旨在最小化与完全重新训练的差距。 AI
影响 这些新的遗忘技术可以通过提供更可控的方式来移除特定数据的影响，从而改善数据隐私和模型管理。
排序理由 两篇在arXiv上发表的学术论文，提出了机器学习遗忘的新方法。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2606.02119v1 Announce Type: cross Abstract: Machine unlearning aims to remove the influence of specific forget training data due to privacy, copyright or bias concerns while maintaining the model performance on the remaining retain data. Existing unlearning algorithms, such…
arXiv:2606.00399v1 Announce Type: new Abstract: Machine unlearning aims to remove the influence of specific training samples while preserving the model's utility. Existing single-objective approaches, such as gradient ascent or random relabeling, often induce catastrophic forgett…
Machine unlearning aims to remove the influence of specific forget training data due to privacy, copyright or bias concerns while maintaining the model performance on the remaining retain data. Existing unlearning algorithms, such as optimizing a weighted combination of losses, h…