Saved in:
Bibliographic Details
Main Authors: Wei, Ganchao, Pearson, John
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.07746
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909026680307712
author Wei, Ganchao
Pearson, John
author_facet Wei, Ganchao
Pearson, John
contents High-dimensional count data arise in applications such as single-cell RNA sequencing and neural spike trains, where mapping between distributions across successive batches or time points form critical components of data analysis. The recent success of diffusion- and flow-based deep generative models for images, video, and text motivates extending these ideas to count-valued settings, but many existing methods either treat each count as a categorical state or transform counts into a continuous space, neither of which is natural or efficient when the count range is large. We propose count-FM, a flow-matching framework for count data based on a continuous-time birth-death process with local unit jumps. Count-FM learns marginal transitions efficiently in count space through simulation-free training of conditional transition rates, allowing transport between arbitrary count-distributed source and target populations. In simulation, count-FM achieves better sample quality than representative baselines while using substantially fewer parameters. We further apply count-FM to scRNA-seq and neural spike-train data for unconditional generation, transport, and conditional generation. Across these tasks, count-FM yields improved sample quality, greater modeling efficiency, and interpretable transport paths.
format Preprint
id arxiv_https___arxiv_org_abs_2605_07746
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Flow Matching for Count Data
Wei, Ganchao
Pearson, John
Machine Learning
Quantitative Methods
High-dimensional count data arise in applications such as single-cell RNA sequencing and neural spike trains, where mapping between distributions across successive batches or time points form critical components of data analysis. The recent success of diffusion- and flow-based deep generative models for images, video, and text motivates extending these ideas to count-valued settings, but many existing methods either treat each count as a categorical state or transform counts into a continuous space, neither of which is natural or efficient when the count range is large. We propose count-FM, a flow-matching framework for count data based on a continuous-time birth-death process with local unit jumps. Count-FM learns marginal transitions efficiently in count space through simulation-free training of conditional transition rates, allowing transport between arbitrary count-distributed source and target populations. In simulation, count-FM achieves better sample quality than representative baselines while using substantially fewer parameters. We further apply count-FM to scRNA-seq and neural spike-train data for unconditional generation, transport, and conditional generation. Across these tasks, count-FM yields improved sample quality, greater modeling efficiency, and interpretable transport paths.
title Flow Matching for Count Data
topic Machine Learning
Quantitative Methods
url https://arxiv.org/abs/2605.07746