Generative Unordered Flow for Set-Structured Data Generation

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Li, Yangming, Liu, Chaoyu, Schönlieb, Carola-Bibiane
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912412446228480
author Li, Yangming
Liu, Chaoyu
Schönlieb, Carola-Bibiane
author_facet Li, Yangming
Liu, Chaoyu
Schönlieb, Carola-Bibiane
contents Flow-based generative models have demonstrated promising performance across a broad spectrum of data modalities (e.g., image and text). However, there are few works exploring their extension to unordered data (e.g., spatial point set), which is not trivial because previous models are mostly designed for vector data that are naturally ordered. In this paper, we present unordered flow, a type of flow-based generative model for set-structured data generation. Specifically, we convert unordered data into an appropriate function representation, and learn the probability measure of such representations through function-valued flow matching. For the inverse map from a function representation to unordered data, we propose a method similar to particle filtering, with Langevin dynamics to first warm-up the initial particles and gradient-based search to update them until convergence. We have conducted extensive experiments on multiple real-world datasets, showing that our unordered flow model is very effective in generating set-structured data and significantly outperforms previous baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2501_17770
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Generative Unordered Flow for Set-Structured Data Generation
Li, Yangming
Liu, Chaoyu
Schönlieb, Carola-Bibiane
Machine Learning
Flow-based generative models have demonstrated promising performance across a broad spectrum of data modalities (e.g., image and text). However, there are few works exploring their extension to unordered data (e.g., spatial point set), which is not trivial because previous models are mostly designed for vector data that are naturally ordered. In this paper, we present unordered flow, a type of flow-based generative model for set-structured data generation. Specifically, we convert unordered data into an appropriate function representation, and learn the probability measure of such representations through function-valued flow matching. For the inverse map from a function representation to unordered data, we propose a method similar to particle filtering, with Langevin dynamics to first warm-up the initial particles and gradient-based search to update them until convergence. We have conducted extensive experiments on multiple real-world datasets, showing that our unordered flow model is very effective in generating set-structured data and significantly outperforms previous baselines.
title Generative Unordered Flow for Set-Structured Data Generation
topic Machine Learning
url https://arxiv.org/abs/2501.17770