Saved in:
Bibliographic Details
Main Authors: Cai, Wenxi, Wang, Yuheng, Shi, Naichen
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.23015
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908614237618176
author Cai, Wenxi
Wang, Yuheng
Shi, Naichen
author_facet Cai, Wenxi
Wang, Yuheng
Shi, Naichen
contents We introduce Coupled Flow Matching (CPFM), a framework that integrates controllable dimensionality reduction and high-fidelity reconstruction. CPFM learns coupled continuous flows for both the high-dimensional data x and the low-dimensional embedding y, which enables sampling p(y|x) via a latent-space flow and p(x|y) via a data-space flow. Unlike classical dimension-reduction methods, where information discarded during compression is often difficult to recover, CPFM preserves the knowledge of residual information within the weights of a flow network. This design provides bespoke controllability: users may decide which semantic factors to retain explicitly in the latent space, while the complementary information remains recoverable through the flow network. Coupled flow matching builds on two components: (i) an extended Gromov-Wasserstein optimal transport objective that establishes a probabilistic correspondence between data and embeddings, and (ii) a dual-conditional flow-matching network that extrapolates the correspondence to the underlying space. Experiments on multiple benchmarks show that CPFM yields semantically rich embeddings and reconstructs data with higher fidelity than existing baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2510_23015
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Coupled Flow Matching
Cai, Wenxi
Wang, Yuheng
Shi, Naichen
Machine Learning
We introduce Coupled Flow Matching (CPFM), a framework that integrates controllable dimensionality reduction and high-fidelity reconstruction. CPFM learns coupled continuous flows for both the high-dimensional data x and the low-dimensional embedding y, which enables sampling p(y|x) via a latent-space flow and p(x|y) via a data-space flow. Unlike classical dimension-reduction methods, where information discarded during compression is often difficult to recover, CPFM preserves the knowledge of residual information within the weights of a flow network. This design provides bespoke controllability: users may decide which semantic factors to retain explicitly in the latent space, while the complementary information remains recoverable through the flow network. Coupled flow matching builds on two components: (i) an extended Gromov-Wasserstein optimal transport objective that establishes a probabilistic correspondence between data and embeddings, and (ii) a dual-conditional flow-matching network that extrapolates the correspondence to the underlying space. Experiments on multiple benchmarks show that CPFM yields semantically rich embeddings and reconstructs data with higher fidelity than existing baselines.
title Coupled Flow Matching
topic Machine Learning
url https://arxiv.org/abs/2510.23015