PulseAugur
EN
LIVE 12:06:50

New framework models probability distributions on metric graphs

Researchers have developed a novel deep generative modeling framework designed for probability distributions on metric graphs. This method embeds graphs into ambient spaces to solve optimal transport problems, projecting generated samples back onto the graph. The approach demonstrates improved scalability and performance compared to heuristic baselines, particularly on real-world urban mobility data. AI

RANK_REASON The cluster describes a new academic paper detailing a novel generative modeling framework.

Read on arXiv stat.ML →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

COVERAGE [2]

  1. arXiv cs.LG TIER_1 English(EN) · Alessandro Micheli, Yueqi Cao, Anthea Monod, Samir Bhatt ·

    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 …

  2. arXiv stat.ML TIER_1 English(EN) · Samir Bhatt ·

    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…