用流匹配方法学习解耦表示，提升语义对齐与可控性
Disentangled Representation Learning via Flow Matching
- 将解耦学习建模为紧凑隐空间中的因子条件流
- 引入正交正则化，显著降低因子间干扰与信息泄露
- 在多个数据集上实现更高解耦度、更好生成质量与可控性
解耦表示学习旨在捕捉观测数据背后的解释性因素，从而深入理解数据生成过程。近年来生成模型的发展为学习此类表示提供了新范式。然而，现有基于扩散的方法依赖归纳偏置实现因子独立性，但常缺乏强语义对齐。本文提出一种基于流匹配的解耦表示学习框架，将解耦视为在紧凑隐空间中学习因子条件流。为强制显式语义对齐，引入非重叠（正交性）正则化，抑制跨因子干扰并减少因子间信息泄漏。在多个数据集上的大量实验表明，该方法持续优于代表性基线，在解耦度、可控性及样本保真度方面均有提升。
原文摘要 · Abstract (English)
Disentangled representation learning aims to capture the underlying explanatory factors of observed data, enabling a principled understanding of the data-generating process. Recent advances in generative modeling have introduced new paradigms for learning such representations. However, existing diffusion-based methods encourage factor independence via inductive biases, yet frequently lack strong semantic alignment. In this work, we propose a flow matching-based framework for disentangled representation learning, which casts disentanglement as learning factor-conditioned flows in a compact latent space. To enforce explicit semantic alignment, we introduce a non-overlap (orthogonality) regularizer that suppresses cross-factor interference and reduces information leakage between factors. Extensive experiments across multiple datasets demonstrate consistent improvements over representative baselines, yielding higher disentanglement scores as well as improved controllability and sample fidelity.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。