Machine Unlearning on CIFAR-10 50% sample-wise unlearning benchmark leaderboard · SOTA2 Research

Machine Unlearning on CIFAR-10 50% sample-wise unlearning

99.45Accuracy (Df)Original

Evaluation Results

Method	Links
Original2025.08		99.45	99.54	94.61	0.01	—	—
SSD2025.08		77.48	77.49	72.63	0.4	0.44	64
RL2025.08		74.33	72.52	67.56	0.11	0.63	116
SCAR*2025.08		73.82	77.8	74.59	0.44	0.36	2,902
GA2025.08		73.78	73.92	71.77	0.36	0.49	51
IU*2025.08		73.01	73.56	61.33	0.23	0.76	52
Retrain2025.08		73	82.74	80.56	0.58	0	—
NPO2025.08		72.95	72	70.11	0.34	0.51	164
IMU2025.08		72.94	78.97	76.64	0.46	0.31	166