PulseAugur
实时 10:25:38
English(EN) MUGEN: Generating Unlearnable Graph Examples for Multiple Learning Tasks

MUGEN框架为多种机器学习任务生成不可学图示例

研究人员开发了MUGEN,一个旨在创建“不可学”图示例的新颖框架,可同时保护跨多个机器学习任务的数据。与之前专注于单一任务的方法不同,MUGEN生成一个单一的扰动数据集,以防止对节点分类、图分类和链接预测等各种应用的未经授权的表示学习。该框架利用任务对齐可分性目标(TASO)和类型自适应扰动(TAP)来确保在扰动数据上训练的模型无法泛化到干净数据,并在不同的GNN骨干网络和学习范式中证明了有效性。 AI

影响 通过防止未经授权的学习,增强了基于图的机器学习应用的数据隐私和安全性。

排序理由 该集群描述了一篇详细介绍生成不可学图示例的新颖框架的新研究论文。

在 Hugging Face Daily Papers 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

MUGEN框架为多种机器学习任务生成不可学图示例

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
该集群描述了一篇详细介绍生成不可学图示例的新颖框架的新研究论文。
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
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
13 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准

报道来源 [2]

  1. arXiv cs.LG TIER_1 English(EN) · Ziyan Liu, Chengshuai Zhao, Huan Liu ·

    MUGEN:为多种学习任务生成不可学图示例

    arXiv:2609.00696v1 Announce Type: new Abstract: Graph data across diverse domains can expose valuable relational information to unauthorized representation learning, creating a pressing need for protection against such misuse. Unlearnable examples offer a data-level defense by pe…

  2. Hugging Face Daily Papers TIER_1 English(EN) ·

    MUGEN:为多种学习任务生成不可学图示例

    Graph data across diverse domains can expose valuable relational information to unauthorized representation learning, creating a pressing need for protection against such misuse. Unlearnable examples offer a data-level defense by perturbing a training release so that models train…