PruneForget：视觉模型的联合遗忘与剪枝
PruneForget: Joint Unlearning and Pruning of Vision Models
浏览论文内容
中文总结 AI 辅助
针对遗忘与剪枝独立处理的问题，提出PruneForget方法，利用遗忘集指导剪枝，联合优化使两者互益，在图像分类和生成模型上消除遗忘样本影响并降低推理成本，性能接近oracle。
中文摘要 AI 辅助
在现实世界中，机器遗忘与模型剪枝日益紧密地联系在一起。模型必须支持遗忘请求（例如出于安全考虑），同时也要满足延迟和内存预算方面的要求。直到最近，现有工作仍将每个方面视为独立问题，例如顺序地执行遗忘和剪枝。在这项工作中，我们表明遗忘和剪枝天然地对齐，应该联合解决以使彼此相互感知。直观地说，编码了被遗忘样本信息的参数是自然的剪枝目标，因为遗忘和剪枝都要求“删除”此类参数。我们提出了PruneForget，一种使用遗忘集作为剪枝指导的方法，从而使遗忘和剪枝相互受益。在图像分类器和生成模型上的大量实验表明，PruneForget消除了被遗忘样本的影响，同时产生了一个推理成本降低的更紧凑模型。相对于从头开始重新训练以进行遗忘然后剪枝的oracle，它实现了可忽略的性能差距。
英文摘要
Machine unlearning and model pruning are increasingly coupled in the real world. Models must support unlearning requests, e.g., for safety concerns, while also meeting requirements in latency and memory budget. Until recently, existing works have studied each aspect as an independent problem, e.g., running unlearning and pruning sequentially. In this work, we show that unlearning and pruning are naturally aligned and should be solved jointly to be made aware of each other. Intuitively, parameters that encode information of the unlearned samples are natural pruning targets, as unlearning and pruning both call for the "deletion" of such parameters. We propose PruneForget, a method that uses the unlearn set as a guide for pruning, so that unlearning and pruning mutually benefit each other. Extensive experiments on image classifiers and generative models show that PruneForget removes the influence of the unlearned samples while producing a more compact model with reduced inference cost. It achieves a negligible performance gap relative to an oracle that retrains from scratch for unlearning and then prunes.
