Machine Unlearning on CIFAR-10 50% random unlearning
83.63PGHIU
Evaluation results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| IUBackbone=ResNet182026.03 | 83.63 | 8.29 | 74.83 | 83.32 | 83.29 | 16.71 | 74.53 | 16.55 | |
| BEBackbone=ResNet182026.03 | 34.7 | 1.22 | 17.33 | 25.81 | 25.93 | 74.07 | 23.37 | 67.71 | |
| BSBackbone=ResNet182026.03 | 26.55 | 0.85 | 8.82 | 17.3 | 17.36 | 82.64 | 15.39 | 75.69 | |
| MUNBaBackbone=ResNet182026.03 | 12.94 | 1.5 | 2.62 | 5.86 | 3.26 | 96.74 | 2.09 | 88.99 | |
| l1-sparseBackbone=ResNet182026.03 | 8.53 | 0.35 | 7.53 | 0.95 | 0.14 | 99.86 | 2.67 | 93.75 | |
| FTBackbone=ResNet182026.03 | 8.5 | 0.36 | 7.52 | 0.96 | 0.18 | 99.82 | 2.67 | 93.75 | |
| GABackbone=ResNet182026.03 | 8.05 | 0.37 | 7.94 | 0.54 | 0.49 | 99.51 | 3.45 | 94.53 | |
| SalUnBackbone=ResNet182026.03 | 7.94 | 0.33 | 7.34 | 1.14 | 0.52 | 99.48 | 2.53 | 93.61 | |
| SPMBackbone=ResNet18-SPM2026.03 | 7.83 | 0.36 | 4.87 | 0.02 | 4.02 | 99.98 | 3.37 | 94.45 | |
| RetrainBackbone=ResNet182026.03 | 0 | 0 | 0 | 8.48 | 0 | 100 | 0 | 91.08 | |
| RetrainBackbone=ResNet18-KNN2026.03 | 0 | 0 | 0 | 0.02 | 0 | 99.98 | 0 | 94.45 | |
| RetrainBackbone=ResNet18-SPM2026.03 | 0 | 0 | 0 | 4.89 | 0 | 95.96 | 0 | 91.08 |