Random-Set GNNs 增强图学习中的不确定性量化

作者 PulseAugur 编辑部 · [2 个来源] · 2026-05-12 11:38

研究人员引入了随机集图神经网络（RS-GNNs）来解决图学习中的不确定性量化问题。该新框架使用证据函数形式主义来模拟节点级别的认知不确定性。在包括自动驾驶基准在内的九个数据集上的实验表明，RS-GNNs 提供了改进的不确定性估计能力。 AI

影响通过量化预测中的不确定性，提高了基于图的人工智能系统的可靠性。

排序理由该集群包含一篇详细介绍新模型架构及其实验验证的学术论文。

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

报道来源 [2]

arXiv stat.ML TIER_1 English(EN) · Tommy Woodley, Shireen Kudukkil Manchingal, Matteo Tolloso, Davide Bacciu, Fabio Cuzzolin · 2026-05-13 04:00

随机集图神经网络

arXiv:2605.11987v1 Announce Type: cross Abstract: Uncertainty quantification has become an important factor in understanding the data representations produced by Graph Neural Networks (GNNs). Despite their predictive capabilities being ever useful across industrial workspaces, th…
arXiv stat.ML TIER_1 English(EN) · Fabio Cuzzolin · 2026-05-12 11:38

随机集图神经网络

Uncertainty quantification has become an important factor in understanding the data representations produced by Graph Neural Networks (GNNs). Despite their predictive capabilities being ever useful across industrial workspaces, the inherent uncertainty induced by the nature of th…