Loading
Life sciences · Preprint
arXiv · September 8, 2026
Posted before peer review. The findings may change or fail to hold.
This is a preprint describing CUNO, a curriculum-based machine-learning framework designed to improve graph unlearning performance under large-scale data deletion. The work is computational and algorithmic in nature, with no clinical, epidemiological, or translational content; it presents benchmark results on synthetic or standard datasets but has not undergone peer review.
Preprint.
At 20% deletion, CUNO retains 74% of original utility compared to 26–53% for existing methods CUNO maintains more than half the original utility even at 50% deletion Curriculum-based progressive removal and negative preference optimization reduce catastrophic unlearning
Safety was not reported in the material analysed. Check the source before drawing any conclusion about harm.
The source did not state who this applies to in practice.
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.
Quoted from the source exactly as published.
Graded across the dimensions that decide whether you should act, each from what the source actually supports. There is no single score, and where a dimension was not assessed it says so.
Graph unlearning removes the influence of designated training data from a trained graph model without retraining from scratch. However, existing methods suffer a sharp drop in model utility under large deletion ratios (mass deletion), a phenomenon we refer to as catastrophic unlearning. We find that a key cause is the uniform treatment of all deleted samples, which is particularly damaging in graph learning: structural dependencies cause different nodes to play vastly different roles in the learned model, yet existing methods apply the same forgetting operation to the entire forget set. Based on this insight, we propose CUNO, a curriculum-based graph unlearning framework that removes the forget set progressively, ordering samples by their estimated unlearning difficulty across multiple stages. CUNO further employs a distribution-level negative preference optimization (NPO) objective at each curriculum stage that steers the model away from its original behavior on the current forget subset while preserving retained performance. Our theoretical analysis shows that the curriculum design is most beneficial when the forget set spans a wide range of unlearning difficulty, a condition naturally satisfied under mass deletion. Comprehensive experiments confirm that CUNO consistently mitigates catastrophic unlearning: at 20% deletion, it retains 74% of the original utility compared to 26-53% for existing methods, and maintains more than half the original utility even at 50% deletion. Our code is publicly available at https://anonymous.4open.science/r/cuno-D4FF.
Taken from the source record, never inferred. Follow any of these and new work involving them reaches your briefing.