Pullback Flow Matching on Data Manifolds
We propose Pullback Flow Matching (PFM), a novel framework for generative modeling on data manifolds. Unlike existing methods that assume or learn restrictive closed-form manifold mappings for training Riemannian Flow Matching (RFM) models, PFM leverages pullback geometry and isometric learning to p...
Gespeichert in:
Hauptverfasser: | , , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | We propose Pullback Flow Matching (PFM), a novel framework for generative
modeling on data manifolds. Unlike existing methods that assume or learn
restrictive closed-form manifold mappings for training Riemannian Flow Matching
(RFM) models, PFM leverages pullback geometry and isometric learning to
preserve the underlying manifold's geometry while enabling efficient generation
and precise interpolation in latent space. This approach not only facilitates
closed-form mappings on the data manifold but also allows for designable latent
spaces, using assumed metrics on both data and latent manifolds. By enhancing
isometric learning through Neural ODEs and proposing a scalable training
objective, we achieve a latent space more suitable for interpolation, leading
to improved manifold learning and generative performance. We demonstrate PFM's
effectiveness through applications in synthetic data, protein dynamics and
protein sequence data, generating novel proteins with specific properties. This
method shows strong potential for drug discovery and materials science, where
generating novel samples with specific properties is of great interest. |
---|---|
DOI: | 10.48550/arxiv.2410.04543 |