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

Machine Unlearning on CIFAR-10 SUBCLASS (deer)

1.9KL Divergence Target (nats)GA

Evaluation Results

Method	Links
GA2026.05		1.9	4.8	2.6	72.4	56.3	8.3
SalUn2026.05		0.37	0.91	0.37	88.7	97.2	17
SCRUB2026.05		0.31	0.28	0.28	95	97.8	22
DIR2026.05		0.23	0.83	0.3	96.3	100	22
RL+FT2026.05		0.22	0.79	0.31	97.1	100	17
FT2026.05		0.13	0.17	0.44	97.9	100	75
GA+FT2026.05		0.12	0.14	0.42	97.8	100	75
pθ2026.05		0.1	—	0.38	98	100	—
LDA-Mix2026.05		0.1	0.09	0.17	96.6	99.8	24
LDA-2C2026.05		0.1	0.1	0.17	96.5	99.7	24
DIR-2C2026.05		0.1	0.1	0.15	96.9	99.8	22
LDA2026.05		0.09	0.1	0.18	97	99.8	24
pθr2026.05		0	—	0	97.7	95.7	100