通过识别影响小的数据点，实现高效无学习，节省近50%计算成本。
When unlearning is free: leveraging low influence points to reduce computational costs
- 筛选对模型影响微乎其微的数据点，优先忽略它们以减少计算量。
- 实测可降低50%的计算开销，且模型性能损失极小。
- 适合需要快速删除数据的隐私保护场景，如医疗或金融建模。
随着机器学习中的数据隐私问题日益突出，能够移除特定数据点的能力变得愈发重要。尽管已有先进的无学习方法，但这些方法通常将遗忘集中的所有数据点一视同仁。本文通过在语言和视觉任务中对比影响函数，识别出对模型输出影响可忽略的训练数据子集。基于此发现，提出一种高效的无学习框架，在无学习前缩小数据集规模，显著降低计算成本。在真实世界实验中，该方法实现了约50%的计算节省。
原文摘要 · Abstract (English)
As concerns around data privacy in machine learning grow, the ability to unlearn, or remove, specific data points from trained models becomes increasingly important. While state of the art unlearning methods have emerged in response, they typically treat all points in the forget set equally. In this work, we challenge this approach by asking whether points that have a negligible impact on the model's learning need to be removed. Through a comparative analysis of influence functions across language and vision tasks, we identify subsets of training data with negligible impact on model outputs. Leveraging this insight, we propose an efficient unlearning framework that reduces the size of datasets before unlearning leading to significant computational savings (up to approximately 50 percent) on real world empirical examples.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。