发表机构
Gaash Lab; National Institute of Technology Srinagar（Gaash实验室; 斯利那加国立理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
UnAct是一种无梯度的类别遗忘方法，仅通过前向传播和激活干预即可高效遗忘，在数据稀缺时优于现有方法，且保持高保留准确率。
AI 中文摘要
机器遗忘旨在从已训练模型中移除指定训练数据的影响，而无需从头重新训练。诸如选择性突触抑制（SSD）及其无标签变体LFSSD等免重训练方法避免了完整的重训练，但仍需要反向传播以及在完整数据集上计算的参数重要性。我们提出一个问题：当删除请求仅附带少数几个待遗忘类别的图像时，会发生什么？为了回答这个问题，我们引入了UnAct，一种无梯度的类别遗忘方法，它仅需要对遗忘图像进行前向传播。UnAct根据晚期层单元的反应对其进行评分，衰减反应最强烈的连接，并在最多20轮中重复此过程，全程不使用梯度、标签或保留数据。在使用CIFAR-10、CIFAR-20和CIFAR-100训练的ResNet-18上，当遗忘整个类别时，UnAct与SSD和LFSSD表现相当，并且与它们不同，在遗忘数据稀缺时，UnAct不会导致网络崩溃。在ResNet-18上，在所有测试规模下，UnAct的保留准确率与重训练的差距保持在2.5个百分点以内，而SSD和LFSSD在其全类别工作点上，在某些类别上损失高达86个百分点。在CIFAR-10上使用五个遗忘图像时，UnAct与重训练的距离为0.21个百分点，而LFSSD为67，SSD为90，并且使用预言机在每个规模下重新选择SSD的阈值并不能缩小这一差距。在初步迁移到ViT-B/16时，UnAct与重训练的距离为11.5，而SSD为33.7，并且当SSD在请求时计算其重要性时，UnAct的请求速度比SSD快19倍。代码可在以下网址获取：此https URL
英文摘要
Machine unlearning seeks to remove the influence of designated training data from a trained model without retraining from scratch. Retrain-free methods such as Selective Synaptic Dampening (SSD) and its label-free variant LFSSD avoid full retraining but still require backpropagation and parameter importance computed over the entire dataset. We ask: what happens when a deletion request arrives with only a few images of the class to be forgotten? To answer this question, we introduce UnAct, a gradient-free class-unlearning method that needs only forward passes over the forget images. UnAct scores late-layer units by their responses, attenuates the most responsive connections, and repeats this for up to 20 rounds using no gradients, no labels, and no retained data. On ResNet-18 trained with CIFAR-10, CIFAR-20, and CIFAR-100, UnAct is competitive with SSD and LFSSD when forgetting entire classes and, unlike them, never collapses the network when forget data is scarce. On ResNet-18, across all tested sizes, UnAct's retain accuracy stays within 2.5 points of retraining, while SSD and LFSSD, at their full-class operating points, lose up to 86 points on some classes. With five forget images on CIFAR-10, UnAct's distance to retraining is 0.21 points, against 67 for LFSSD and 90 for SSD, and re-selecting SSD's threshold at each size with an oracle does not close the gap. In preliminary transfer to ViT-B/16, UnAct's distance to retraining is 11.5 against 33.7 for SSD, and a request is 19x faster than SSD when SSD computes its importance at request time. The code is available at https://github.com/abdulmuizz0903/UnAct
