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

• URL: http://arxiv.org/abs/2609.08244v1
• Date: Tue, 08 Sep 2026 04:39:34 GMT
• Title: CUNO: Curriculum and Preference Optimization for Stable Graph Unlearning under Mass Deletion
• Abstract summary: Graph unlearning removes the influence of designated training data from a trained graph model without retraining from scratch.<n>We propose CUNO, a curriculum-based graph unlearning framework that removes the forget set progressively.<n>CUNO consistently mitigates catastrophic unlearning and maintains more than half the original utility even at 50% deletion.
• Score: 9.068618482899327
• License: http://creativecommons.org/licenses/by-sa/4.0/
• 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.

Related papers

• What to Forget in Unlearning? Forget Set Curation for Language Models [24.23267387545857]
  We show how a requester may ask a model to stop reproducing a song or book without knowing which spans, documents, quotations, or near-duplicates support that behavior.<n>We introduce CleanSlate, a benchmark for verbatim output suppression over songs and books, with model-specific extraction profiles, content-grounded QA, and capability-retention evaluations.
  arXiv  Detail & Related papers  (2026-08-14T19:51:53Z)
• Fast Unlearning at Scale via Margin Self-Correction [52.46927918952516]
  Language-model unlearning updates a trained model to behave as if it had not seen selected training examples.<n>MASC achieves a competitive forget-retain trade-off at a fraction of the computational cost of existing baselines.
  arXiv  Detail & Related papers  (2026-06-01T21:49:54Z)
• Not Every Subject Should Stay: Machine Unlearning for Noisy Engagement Recognition [53.005382593686356]
  Engagement recognition datasets are typically subject-indexed and often contain noisy, subjective supervision.<n>We study this setting through subject-level machine unlearning as a post-hoc sanitization mechanism for engagement recognition.
  arXiv  Detail & Related papers  (2026-05-06T10:03:06Z)
• The Right to be Forgotten in Pruning: Unveil Machine Unlearning on Sparse Models [18.728123679646398]
  Machine unlearning aims to efficiently eliminate the memory about deleted data from trained models and address the right to be forgotten.<n>In this paper, we empirically find that the deleted data has an impact on the pruned topology in a sparse model.<n>Motivated by the observation and the right to be forgotten, we define a new terminology un-pruning" to eliminate the impact of deleted data on model pruning.
  arXiv  Detail & Related papers  (2025-07-24T18:13:26Z)
• Model Collapse Is Not a Bug but a Feature in Machine Unlearning for LLMs [54.167494079321465]
  Current unlearning methods for LLMs optimize on the private information they seek to remove by incorporating it into their fine-tuning data.<n>We propose a novel unlearning method-Partial Model Collapse (PMC), which does not require unlearning targets in the unlearning objective.
  arXiv  Detail & Related papers  (2025-07-06T03:08:49Z)
• Distillation Robustifies Unlearning [36.27570321651185]
  We show that training a model can drastically modify its input-output behavior while leaving its underlying capabilities intact.<n>We propose Unlearn-Noise-Distill-on-Outputs (UNDO), a scalable method that distills an unlearned model into a noised copy of itself.
  arXiv  Detail & Related papers  (2025-06-06T17:58:54Z)
• UPCORE: Utility-Preserving Coreset Selection for Balanced Unlearning [57.081646768835704]
  User specifications or legal frameworks often require information to be removed from pretrained models, including large language models (LLMs)<n>This requires deleting or "forgetting" a set of data points from an already-trained model, which typically degrades its performance on other data points.<n>We propose UPCORE, a method-agnostic data selection framework for mitigating collateral damage during unlearning.
  arXiv  Detail & Related papers  (2025-02-20T22:51:10Z)
• Learn to Unlearn for Deep Neural Networks: Minimizing Unlearning Interference with Gradient Projection [56.292071534857946]
  Recent data-privacy laws have sparked interest in machine unlearning. Challenge is to discard information about the forget'' data without altering knowledge about remaining dataset. We adopt a projected-gradient based learning method, named as Projected-Gradient Unlearning (PGU) We provide empirically evidence to demonstrate that our unlearning method can produce models that behave similar to models retrained from scratch across various metrics even when the training dataset is no longer accessible.
  arXiv  Detail & Related papers  (2023-12-07T07:17:24Z)
• SecureCut: Federated Gradient Boosting Decision Trees with Efficient Machine Unlearning [10.011146979811752]
  It has become imperative to enable data removal in Vertical Federated Learning (VFL) where multiple parties provide private features for model training. In VFL, data removal, i.e., textitmachine unlearning, often requires removing specific features across all samples under privacy guarentee. We propose methname, a novel Gradient Boosting Decision Tree (GBDT) framework that effectively enables both textitinstance unlearning and textitfeature unlearning without the need for retraining from scratch.
  arXiv  Detail & Related papers  (2023-11-22T05:38:53Z)
• Machine Unlearning of Features and Labels [72.81914952849334]
  We propose first scenarios for unlearning and labels in machine learning models. Our approach builds on the concept of influence functions and realizes unlearning through closed-form updates of model parameters.
  arXiv  Detail & Related papers  (2021-08-26T04:42:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.