Machine Unlearning on CIFAR100 scenario SUBCLASS (apple) (test) benchmark leaderboard · SOTA2 Research

Machine Unlearning on CIFAR100 scenario SUBCLASS (apple) (test)

0KL Divergence (Test Set)pθr

Evaluation Results

Method	Links
pθr2026.05		0	—	0	92.3	96.2	100
pθ2026.05		0.08	—	0.35	92.4	100	—
LDA-Mix2026.05		0.09	0.09	0.12	92.2	94.9	1.5
DIR2026.05		0.09	0.15	0.31	92.2	84.5	1.1
DIR-2C2026.05		0.09	0.09	0.18	92.2	98.7	1.2
SCRUB2026.05		0.09	0.09	0.28	92.3	98.2	0.63
SalUn2026.05		0.09	0.52	0.1	92.3	96.7	0.45
RL+FT2026.05		0.09	0.26	0.16	92.2	93.2	0.6
GA2026.05		0.09	4.2	0.13	92.2	93.3	0.21
LDA-2C2026.05		0.1	0.09	0.32	92.1	100	1.2
LDA2026.05		0.11	0.09	0.32	91.9	100	1.2
FT2026.05		0.12	0.13	0.29	91.9	100	17
GA+FT2026.05		0.13	0.13	0.19	91.6	98.8	17