Machine Unlearning on CIFAR-10 forget split (10%)
100AccuracyBadT
Evaluation results
| Method | Links | ||
|---|---|---|---|
| BadTBackbone=ResNet-18, Number of trials=3, Run Time Efficiency (s)=182.782025.04 | 100 | 60.33 | |
| SalUnBackbone=ResNet-18, Number of trials=3, Run Time Efficiency (s)=150.512025.04 | 100 | 63.61 | |
| ESCBackbone=ResNet-18, Number of trials=3, Uses Retain set (Dr)=false, Run Time Efficiency (s)=2.242025.04 | 100 | 73.43 | |
| SCRUBBackbone=ResNet-18, Number of trials=3, Uses Retain set (Dr)=true, Run Time Efficiency (s)=160.392025.04 | 99.99 | 86.41 | |
| ESC-TBackbone=ResNet-18, Number of trials=3, Uses Retain set (Dr)=false, Run Time Efficiency (s)=29.472025.04 | 99.86 | 76.74 | |
| FinetuneBackbone=ResNet-18, Number of trials=3, Run Time Efficiency (s)=132.022025.04 | 99.85 | 87.73 | |
| NGBackbone=ResNet-18, Number of trials=3, Run Time Efficiency (s)=26.792025.04 | 96.57 | 79.26 | |
| RLBackbone=ResNet-18, Number of trials=3, Run Time Efficiency (s)=2.572025.04 | 94.52 | 27.99 | |
| RetrainBackbone=ResNet-18, Number of trials=3, Run Time Efficiency (s)=2681.722025.04 | 10 | 74.64 |