Machine Unlearning on CIFAR-10 SUBCLASS (deer) (forget/retain) benchmark leaderboard · SOTA2 Research

Machine Unlearning on CIFAR-10 SUBCLASS (deer) (forget/retain)

0KL Divergence (Test)pθr

Evaluation Results

Method	Links
pθr2026.05		0	—	0	99.6	98	100
LDA-Mix2026.05		0.01	0.01	0.11	99.7	100	5.1
LDA-2C2026.05		0.01	0.01	0.08	99.7	99.9	4.7
SCRUB2026.05		0.01	2.3	0.11	99.6	99	6.2
FT2026.05		0.01	0.01	0.13	99.7	99.8	17
pθ2026.05		0.02	—	0.22	99.7	100	—
LDA2026.05		0.02	0.02	0.18	99.6	100	4.8
DIR-2C2026.05		0.02	0.02	0.15	99.6	99.2	4.7
GA+FT2026.05		0.16	0.16	1.7	98	81.4	18
DIR2026.05		0.65	0.75	6.6	90.5	10.3	4.6
RL+FT2026.05		0.66	0.76	6.7	90.5	10.4	4.1
SalUn2026.05		1	1	10	88.4	1	4.4
GA2026.05		13	1,338	46	45.5	0	2