Scissorhands:通过网络中的连接敏感性清除数据影响
Scissorhands: Scrub Data Influence via Connection Sensitivity in Networks
AI总结:
Scissorhands通过连接敏感性识别并重新初始化关键参数,结合梯度投影微调,实现高效机器遗忘,在图像任务上表现优异。
摘要:
机器遗忘已成为从训练模型中擦除数据影响的关键任务。它遵循最新的数据法规标准,并增强了机器学习应用的隐私和安全性。在这项工作中,我们提出了一种新的机器遗忘方法Scissorhands。最初,Scissorhands通过连接敏感性识别给定模型中与遗忘数据最相关的参数。通过重新初始化这些参数中最有影响力的前k%参数,获得一个用于擦除遗忘数据影响的修剪模型。随后,Scissorhands使用基于梯度投影的方法对修剪模型进行微调,寻找在保留剩余数据信息的同时丢弃与遗忘数据相关信息的参数。我们在图像分类和图像生成任务上进行的实验结果表明,与现有方法相比,Scissorhands展示了具有竞争力的性能。源代码可在https://github.com/JingWu321/Scissorhands获取。
英文摘要:
Machine unlearning has become a pivotal task to erase the influence of data from a trained model. It adheres to recent data regulation standards and enhances the privacy and security of machine learning applications. In this work, we present a new machine unlearning approach Scissorhands. Initially, Scissorhands identifies the most pertinent parameters in the given model relative to the forgetting data via connection sensitivity. By reinitializing the most influential top-k percent of these parameters, a trimmed model for erasing the influence of the forgetting data is obtained. Subsequently, Scissorhands fine-tunes the trimmed model with a gradient projection-based approach, seeking parameters that preserve information on the remaining data while discarding information related to the forgetting data. Our experimental results, conducted across image classification and image generation tasks, demonstrate that Scissorhands, showcases competitive performance when compared to existing methods. Source code is available at https://github.com/JingWu321/Scissorhands.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。