我们提出了耦合流匹配(CPFM),这是一个整合了可控降维与高保真重建的框架。CPFM 学习高维数据 x 和低维嵌入 y 的耦合连续流,从而能够通过潜在空间流采样 p(y|x),并通过数据空间流采样 p(x|y)。与经典降维方法(其中压缩过程中丢弃的信息往往难以恢复)不同,CPFM 将残差信息的知识保留在流网络的权重中。这种设计提供了定制化的可控性:用户可以选择在潜在空间中显式保留哪些语义因素,而互补信息则可以通过流网络恢复。耦合流匹配建立在两个组件之上:(i)扩展的 Gromov-Wasserstein 最优传输目标,用于建立数据与嵌入之间的概率对应关系;(ii)双条件流匹配网络,将该对应关系外推到潜在空间。在多个基准上的实验表明,CPFM 生成的嵌入具有丰富的语义,并且重建数据的保真度高于现有基线方法。
英文摘要:
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.
H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology(哈里·米尔顿·斯图尔特工业与系统工程学院,佐治亚理工学院);Department of Mathematics, Duke University(杜克大学数学系)
On the Closed-Form of Flow Matching: Generalization Does Not Arise from Target Stochasticity
Université Jean Monnet Saint-Étienne, CNRS, Institut d’Optique Graduate School, Inria, Laboratoire Hubert Curien UMR 5516;ENS de Lyon, CNRS, Université Claude Bernard Lyon 1, Inria, LIP UMR 5668;Inria, ENS de Lyon, CNRS, Université Claude Bernard Lyon 1, LIP UMR 5668;Institut Universitaire de France
Flow Matching for Efficient and Scalable Data Assimilation
The Computing and Mathematical Sciences Department, California Institute of Technology(加州理工学院计算与数学科学系);Department of Mathematics and Scientific Computing and Imaging Institute, University of Utah(犹他大学数学与科学计算系和成像研究所)
Center for Foundation Models and Generative AI, Northwestern University(基础模型与生成式人工智能中心,西北大学);Department of Computer Science, Northwestern University(计算机科学系,西北大学);Department of Statistics and Data Science, Northwestern University(统计与数据科学系,西北大学)
Department of Artificial Intelligence, Westlake University, Hangzhou, China(人工智能系,西湖大学,杭州,中国);Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing, China(数学与系统科学研究院,中国科学院,北京,中国)
Hierarchical Discrete Flow Matching for Graph Generation
Department of Computer Science, University of Geneva, Switzerland(瑞士日内瓦大学计算机科学系);DMML Group, Geneva School for Business administration HES-SO, Switzerland(瑞士日内瓦高等商学院DMML研究组)
Booth School of Business, University of Chicago(芝加哥大学布斯商学院);Department of Statistics, University of Michigan(密歇根大学统计系);Department of Mathematics, University of Maryland, College Park(马里兰大学帕克分校数学系)