English(EN) MDTE: Minority-Aware Diffusion over Temporal Edge Events for Imbalanced Node Classification

新的MDTE框架提升了时序图中少数类节点的分类能力

作者 PulseAugur 编辑部 · [1 个来源] · 2026-08-26 04:00

研究人员开发了MDTE，一个旨在改进时序图中节点分类的新框架，特别关注少数类。该方法使用条件扩散去噪来重建时序边事件表示，解决了多数类主导传播可能掩盖少数类信号的挑战。MDTE结合了分布感知选择性传播来过滤有害传播，以及多视图判别性融合来增强类区分度。实验表明，与现有方法相比，MDTE显著提高了少数类的召回率和F1分数。 AI

影响增强了在动态网络结构中识别和分类代表性不足数据点的能力。

排序理由该集群包含一篇学术论文，详细介绍了一种新的节点分类方法。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

arXiv

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: 42 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇学术论文，详细介绍了一种新的节点分类方法。[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, other; 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.LG TIER_1 English(EN) · Zhou Zelong, Zhang Tianming, Yang Zhengyi, Tang Yifu, Hou Chenyu, Cao Bin, Fan Jing · 2026-08-26 04:00

MDTE：用于不平衡节点分类的少数类感知时序边缘事件扩散

arXiv:2608.24812v1 Announce Type: new Abstract: Class-imbalanced node classification on temporal graphs is challenging because majority-dominated temporal propagation progressively assimilates minority representations, while conventional node and neighborhood information provides…

本文如何被排名

报道来源 [1]

MDTE：用于不平衡节点分类的少数类感知时序边缘事件扩散

相关实体

相关话题