CUNO: Curriculum and Preference Optimization for Stable Graph Unlearning under Mass Deletion

2026-09-08

AI Summary

为解决大规模删除下图模型的灾难性遗忘问题，提出CUNO框架，通过逐步移除遗忘集并优化负偏好来保持模型性能。

Abstract

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.

Problem

• Graph Unlearning
• Catastrophic Unlearning
• Mass Deletion
• Model Utility

Innovation

• Curriculum-based Unlearning
• Negative Preference Optimization
• Graph Unlearning
• Mass Deletion
• Catastrophic Unlearning