Machine Unlearning on CIFAR-10 (retain)
100AccuracyRetrain
Evaluation results
| Method | Links | |
|---|---|---|
| RetrainBackbone=ResNet-18, Number of trials=3, Run Time Efficiency (s)=2681.722025.04 | 100 | |
| FinetuneBackbone=ResNet-18, Number of trials=3, Run Time Efficiency (s)=132.022025.04 | 100 | |
| SCRUBBackbone=ResNet-18, Number of trials=3, Uses Retain set (Dr)=true, Run Time Efficiency (s)=160.392025.04 | 100 | |
| BadTBackbone=ResNet-18, Number of trials=3, Run Time Efficiency (s)=182.782025.04 | 100 | |
| ESCBackbone=ResNet-18, Number of trials=3, Uses Retain set (Dr)=false, Run Time Efficiency (s)=2.242025.04 | 100 | |
| SalUnBackbone=ResNet-18, Number of trials=3, Run Time Efficiency (s)=150.512025.04 | 99.99 | |
| RLBackbone=ResNet-18, Number of trials=3, Run Time Efficiency (s)=2.572025.04 | 99.97 | |
| ESC-TBackbone=ResNet-18, Number of trials=3, Uses Retain set (Dr)=false, Run Time Efficiency (s)=29.472025.04 | 97.78 | |
| NGBackbone=ResNet-18, Number of trials=3, Run Time Efficiency (s)=26.792025.04 | 96.59 |