Zero-Flow Encoders

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Yakun, Wang, Leyang, Liu, Song, Suzuki, Taiji
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914298570211328
author Wang, Yakun
Wang, Leyang
Liu, Song
Suzuki, Taiji
author_facet Wang, Yakun
Wang, Leyang
Liu, Song
Suzuki, Taiji
contents Flow-based methods have achieved significant success in various generative modeling tasks, capturing nuanced details within complex data distributions. However, few existing works have exploited this unique capability to resolve fine-grained structural details beyond generation tasks. This paper presents a flow-inspired framework for representation learning. First, we demonstrate that a rectified flow trained using independent coupling is zero everywhere at $t=0.5$ if and only if the source and target distributions are identical. We term this property the \emph{zero-flow criterion}. Second, we show that this criterion can certify conditional independence, thereby extracting \emph{sufficient information} from the data. Third, we translate this criterion into a tractable, simulation-free loss function that enables learning amortized Markov blankets in graphical models and latent representations in self-supervised learning tasks. Experiments on both simulated and real-world datasets demonstrate the effectiveness of our approach. The code reproducing our experiments can be found at: https://github.com/probabilityFLOW/zfe.
format Preprint
id arxiv_https___arxiv_org_abs_2602_00797
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Zero-Flow Encoders
Wang, Yakun
Wang, Leyang
Liu, Song
Suzuki, Taiji
Machine Learning
Flow-based methods have achieved significant success in various generative modeling tasks, capturing nuanced details within complex data distributions. However, few existing works have exploited this unique capability to resolve fine-grained structural details beyond generation tasks. This paper presents a flow-inspired framework for representation learning. First, we demonstrate that a rectified flow trained using independent coupling is zero everywhere at $t=0.5$ if and only if the source and target distributions are identical. We term this property the \emph{zero-flow criterion}. Second, we show that this criterion can certify conditional independence, thereby extracting \emph{sufficient information} from the data. Third, we translate this criterion into a tractable, simulation-free loss function that enables learning amortized Markov blankets in graphical models and latent representations in self-supervised learning tasks. Experiments on both simulated and real-world datasets demonstrate the effectiveness of our approach. The code reproducing our experiments can be found at: https://github.com/probabilityFLOW/zfe.
title Zero-Flow Encoders
topic Machine Learning
url https://arxiv.org/abs/2602.00797