Pullback Flow Matching on Data Manifolds

• URL: http://arxiv.org/abs/2410.04543v1
• Date: Sun, 6 Oct 2024 16:41:26 GMT
• Title: Pullback Flow Matching on Data Manifolds
• Authors: Friso de Kruiff, Erik Bekkers, Ozan Öktem, Carola-Bibiane Schönlieb, Willem Diepeveen,
• Abstract summary: Pullback Flow Matching (PFM) is a framework for generative modeling on data manifold. We demonstrate PFM's effectiveness through applications in synthetic, data 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.
• Score: 10.187244125099479
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 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.

Related papers

• MING: A Functional Approach to Learning Molecular Generative Models [46.189683355768736]
  This paper introduces a novel paradigm for learning molecule generative models based on functional representations. We propose Molecular Implicit Neural Generation (MING), a diffusion-based model that learns molecular distributions in function space.
  arXiv  Detail & Related papers  (2024-10-16T13:02:02Z)
• Generative Modeling on Manifolds Through Mixture of Riemannian Diffusion Processes [57.396578974401734]
  We introduce a principled framework for building a generative diffusion process on general manifold. Instead of following the denoising approach of previous diffusion models, we construct a diffusion process using a mixture of bridge processes. We develop a geometric understanding of the mixture process, deriving the drift as a weighted mean of tangent directions to the data points.
  arXiv  Detail & Related papers  (2023-10-11T06:04:40Z)
• Neural FIM for learning Fisher Information Metrics from point cloud data [71.07939200676199]
  We propose neural FIM, a method for computing the Fisher information metric (FIM) from point cloud data. We demonstrate its utility in selecting parameters for the PHATE visualization method as well as its ability to obtain information pertaining to local volume illuminating branching points and cluster centers embeddings of a toy dataset and two single-cell datasets of IPSC reprogramming and PBMCs (immune cells)
  arXiv  Detail & Related papers  (2023-06-01T17:36:13Z)
• A Heat Diffusion Perspective on Geodesic Preserving Dimensionality Reduction [66.21060114843202]
  We propose a more general heat kernel based manifold embedding method that we call heat geodesic embeddings. Results show that our method outperforms existing state of the art in preserving ground truth manifold distances. We also showcase our method on single cell RNA-sequencing datasets with both continuum and cluster structure.
  arXiv  Detail & Related papers  (2023-05-30T13:58:50Z)
• VTAE: Variational Transformer Autoencoder with Manifolds Learning [144.0546653941249]
  Deep generative models have demonstrated successful applications in learning non-linear data distributions through a number of latent variables. The nonlinearity of the generator implies that the latent space shows an unsatisfactory projection of the data space, which results in poor representation learning. We show that geodesics and accurate computation can substantially improve the performance of deep generative models.
  arXiv  Detail & Related papers  (2023-04-03T13:13:19Z)
• Deep Kernel Methods Learn Better: From Cards to Process Optimization [0.7587345054583298]
  We show that DKL with active learning can produce a more compact and smooth latent space. We demonstrate this behavior using a simple cards data set and extend it to the optimization of domain-generated trajectories in physical systems.
  arXiv  Detail & Related papers  (2023-03-25T20:21:29Z)
• Nonlinear Isometric Manifold Learning for Injective Normalizing Flows [58.720142291102135]
  We use isometries to separate manifold learning and density estimation. We also employ autoencoders to design embeddings with explicit inverses that do not distort the probability distribution.
  arXiv  Detail & Related papers  (2022-03-08T08:57:43Z)
• Inferring Manifolds From Noisy Data Using Gaussian Processes [17.166283428199634]
  Most existing manifold learning algorithms replace the original data with lower dimensional coordinates. This article proposes a new methodology for addressing these problems, allowing the estimated manifold between fitted data points.
  arXiv  Detail & Related papers  (2021-10-14T15:50:38Z)
• Moser Flow: Divergence-based Generative Modeling on Manifolds [49.04974733536027]
  Moser Flow (MF) is a new class of generative models within the family of continuous normalizing flows (CNF) MF does not require invoking or backpropagating through an ODE solver during training. We demonstrate for the first time the use of flow models for sampling from general curved surfaces.
  arXiv  Detail & Related papers  (2021-08-18T09:00:24Z)
• Characterizing the Latent Space of Molecular Deep Generative Models with Persistent Homology Metrics [21.95240820041655]
  Variational Autos (VAEs) are generative models in which encoder-decoder network pairs are trained to reconstruct training data distributions. We propose a method for measuring how well the latent space of deep generative models is able to encode structural and chemical features.
  arXiv  Detail & Related papers  (2020-10-18T13:33:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.