English(EN) CUNO: Curriculum and Preference Optimization for Stable Graph Unlearning under Mass Deletion

新的CUNO框架解决了图模型中的灾难性遗忘问题

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-10 04:00

研究人员开发了CUNO，一个用于图遗忘的新框架，旨在缓解灾难性遗忘，即模型效用随着大量删除数据而急剧下降的现象。CUNO通过根据估计的遗忘难度逐步删除数据样本来解决这个问题，并采用负偏好优化目标来引导模型偏离其原始行为，同时不牺牲保留的性能。实验表明，CUNO显著提高了效用保留率，即使在删除50%的数据时也能保持超过一半的原始性能，优于现有方法。 AI

影响这项研究可以提高从训练模型中选择性删除数据的能力，从而增强基于图的机器学习应用中的隐私和数据管理。

排序理由该集群包含一篇详细介绍图遗忘新方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 12 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍图遗忘新方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Chenhan Zhang, Ali Braytee, Madhushi Bandara, Xin Hao, Paul J. Kennedy, Massimo Piccardi, Raymond Owen · 2026-09-10 04:00

CUNO：大规模删除下稳定图解学的课程与偏好优化

arXiv:2609.08244v1 Announce Type: cross 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 deleti…

本文如何被排名

报道来源 [1]

CUNO：大规模删除下稳定图解学的课程与偏好优化

相关实体

相关话题