新框架对度量图上的概率分布进行建模

作者 PulseAugur 编辑部 · [2 个来源] · 2026-06-15 06:21

研究人员开发了一个新颖的深度生成建模框架，用于度量图上的概率分布。该方法将图嵌入到环境空间中以解决最优传输问题，然后将生成的样本投影回图上。与启发式基线相比，该方法在可扩展性和性能方面均有所提高，尤其是在真实世界的城市出行数据上。 AI

排序理由该集群描述了一篇关于新颖生成建模框架的学术论文。

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 cs.LG TIER_1 English(EN) · Alessandro Micheli, Yueqi Cao, Anthea Monod, Samir Bhatt · 2026-06-16 04:00

Generative Modeling on Metric Graphs via Neural Optimal Transport

arXiv:2606.16273v1 Announce Type: cross Abstract: We introduce, to our knowledge, the first deep generative modeling framework for probability distributions continuously supported on compact metric graphs. Given source and target measures on a metric graph, our method embeds the …
arXiv stat.ML TIER_1 English(EN) · Samir Bhatt · 2026-06-15 06:21

Generative Modeling on Metric Graphs via Neural Optimal Transport

We introduce, to our knowledge, the first deep generative modeling framework for probability distributions continuously supported on compact metric graphs. Given source and target measures on a metric graph, our method embeds the graph into a smooth ambient space, solves an entro…