SVD-guided orthogonal subspace projection in LoRA enables stable performance across 30 sequential unlearning tasks on CIFAR-100 and MNIST, unlike naive static fusion which collapses retained accuracy.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Orthogonal Subspace Projection for Continual Machine Unlearning via SVD-Based LoRA
SVD-guided orthogonal subspace projection in LoRA enables stable performance across 30 sequential unlearning tasks on CIFAR-100 and MNIST, unlike naive static fusion which collapses retained accuracy.