SEP 8, 2026 · PREPRINT
CUNO: Curriculum and Preference Optimization for Stable Graph Unlearning under Mass Deletion
arXiv
This is an unrefereed arXiv preprint presenting a novel machine-learning algorithm for graph unlearning; it has not undergone peer review and cannot be graded on clinical or evidence strength grounds.
Reported
Utility retention at 20% deletion74%
Utility retention at 20% deletion…26–53%
Utility retention at 50% deletionmore than half the original utility