Trans-Dimensional Generative Modeling via Jump Diffusion Models

2023/05/25 by Andrew T. Campbell, Campbell, Andrew, William R. Harvey +9 · 9 citations
Computer Science · Physics and Astronomy · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Gaussian Processes and Bayesian Inference #Generative Adversarial Networks and Image Synthesis #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Model Reduction and Neural Networks

paper · pdf · doi:10.48550/arxiv.2305.16261

openalex publication_date 2023/05/25 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We propose a new class of generative models that naturally handle data of varying dimensionality by jointly modeling the state and dimension of each datapoint. The generative process is formulated as a jump diffusion process that makes jumps between different dimensional spaces. We first define a dimension destroying forward noising process, before deriving the dimension creating time-reversed generative process along with a novel evidence lower bound training objective for learning to approximate it. Simulating our learned approximation to the time-reversed generative process then provides an effective way of sampling data of varying dimensionality by jointly generating state values and dimensions. We demonstrate our approach on molecular and video datasets of varying dimensionality, reporting better compatibility with test-time diffusion guidance imputation tasks and improved interpolation capabilities versus fixed dimensional models that generate state values and dimensions separately.

Cited by

• NEAT: Neighborhood-Guided, Efficient, Autoregressive Set Transformer for 3D Molecular Generation
• Spatiotemporal Pyramid Flow Matching for Climate Emulation
• Branching Flows: Discrete, Continuous, and Manifold Flow Matching with Splits and Deletions
• A Diffusion Model to Shrink Proteins While Maintaining Their Function
• Discrete Bayesian Sample Inference for Graph Generation
• Existence-Field Diffusion Model for Spatial Point Processes with Variable Cardinality
• OneFlow: Concurrent Mixed-Modal and Interleaved Generation with Edit Flows
• Multi-domain Distribution Learning for De Novo Drug Design
• Any-Order Flexible Length Masked Diffusion

Related

• Diffusion Models with Double Guidance: Generate with aggregated datasets
• Dynamical regimes of diffusion models
• Let us Build Bridges: Understanding and Extending Diffusion Generative Models
• Latent Abstractions in Generative Diffusion Models
• VFusion3D: Learning Scalable 3D Generative Models from Video Diffusion Models