Disentangled Representation Learning via Flow Matching

TL;DR

This paper introduces a flow matching framework for disentangled representation learning that emphasizes semantic alignment and reduces factor interference, leading to improved disentanglement and controllability.

Contribution

It proposes a novel flow matching-based method with an orthogonality regularizer to enhance semantic alignment in disentangled representations.

Findings

Achieves higher disentanglement scores across multiple datasets.

Demonstrates improved controllability of generated data.

Yields better sample fidelity compared to baselines.

Abstract

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.