Federated Data-level Unlearning on Fashion-MNIST MINILENET (test)
99.16Pretrain Accuracyf-FUM (KL-KL)
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| f-FUM (KL-KL)N (Number of clients)=10, Removed (%)=2, divergence=KL-KL2026.02 | 99.16 | 79.62 | 49.9 | |
| f-FUM (KL-JS)N (Number of clients)=10, Removed (%)=2, divergence=KL-JS2026.02 | 99.16 | 80.02 | 50.2 | |
| f-FUM (KL-chi^2)N (Number of clients)=10, Removed (%)=2, divergence=KL-chi^22026.02 | 99.16 | 79.28 | 49.7 | |
| NoTN (Number of clients)=10, Removed (%)=22026.02 | 99.16 | 57.77 | 49.5 | |
| HalimiN (Number of clients)=10, Removed (%)=22026.02 | 99.16 | 79.65 | 49.2 | |
| f-FUM (KL-KL)N (Number of clients)=5, Removed (%)=2, divergence=KL-KL2026.02 | 99.16 | 79.33 | 49.33 | |
| f-FUM (KL-JS)N (Number of clients)=5, Removed (%)=2, divergence=KL-JS2026.02 | 99.16 | 79.8 | 48.38 | |
| f-FUM (KL-chi^2)N (Number of clients)=5, Removed (%)=2, divergence=KL-chi^22026.02 | 99.16 | 79.1 | 48.57 | |
| NoTN (Number of clients)=5, Removed (%)=22026.02 | 99.16 | 72.03 | 49.17 | |
| HalimiN (Number of clients)=5, Removed (%)=22026.02 | 99.16 | 79.18 | 50.19 |