用超网络动态生成遗忘数据的模型，实现精准删数不伤性能
Learning to Forget using Hypernetworks
- 用超网络生成无目标数据记忆的模型参数
- 遗忘集准确率归零，保留集性能基本不变
- 适合需要合规删除数据的AI系统
机器遗忘因应对数据污染攻击和满足隐私法规而日益重要。目标是在不损害模型整体性能的前提下，消除训练模型对特定不良数据的影响。本文提出HyperForget框架，利用超网络——即生成其他网络参数的神经网络——动态采样不包含目标数据知识的模型，从而实现针对性遗忘。结合扩散模型，我们构建了两种扩散超网络，并在概念验证实验中成功采样出遗忘模型。实验结果表明，这些模型在遗忘数据集上准确率为零，同时在保留数据集上仍保持良好性能，证明了HyperForget在动态定向数据删除中的潜力，也为开发自适应机器遗忘算法指明了新方向。
原文摘要 · Abstract (English)
Machine unlearning is gaining increasing attention as a way to remove adversarial data poisoning attacks from already trained models and to comply with privacy and AI regulations. The objective is to unlearn the effect of undesired data from a trained model while maintaining performance on the remaining data. This paper introduces HyperForget, a novel machine unlearning framework that leverages hypernetworks - neural networks that generate parameters for other networks - to dynamically sample models that lack knowledge of targeted data while preserving essential capabilities. Leveraging diffusion models, we implement two Diffusion HyperForget Networks and used them to sample unlearned models in Proof-of-Concept experiments. The unlearned models obtained zero accuracy on the forget set, while preserving good accuracy on the retain sets, highlighting the potential of HyperForget for dynamic targeted data removal and a promising direction for developing adaptive machine unlearning algorithms.
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。