Conditioning Score-Based Generative Models by Neuro-Symbolic Constraints

by   Davide Scassola, et al.
University of Trieste

Score-based and diffusion models have emerged as effective approaches for both conditional and unconditional generation. Still conditional generation is based on either a specific training of a conditional model or classifier guidance, which requires training a noise-dependent classifier, even when the classifier for uncorrupted data is given. We propose an approach to sample from unconditional score-based generative models enforcing arbitrary logical constraints, without any additional training. Firstly, we show how to manipulate the learned score in order to sample from an un-normalized distribution conditional on a user-defined constraint. Then, we define a flexible and numerically stable neuro-symbolic framework for encoding soft logical constraints. Combining these two ingredients we obtain a general, but approximate, conditional sampling algorithm. We further developed effective heuristics aimed at improving the approximation. Finally, we show the effectiveness of our approach for various types of constraints and data: tabular data, images and time series.


page 5

page 6


Classifier-Free Diffusion Guidance

Classifier guidance is a recently introduced method to trade off mode co...

Regular Time-series Generation using SGM

Score-based generative models (SGMs) are generative models that are in t...

Score-based Conditional Generation with Fewer Labeled Data by Self-calibrating Classifier Guidance

Score-based Generative Models (SGMs) are a popular family of deep genera...

Score-Based Generative Models for Molecule Generation

Recent advances in generative models have made exploring design spaces e...

Entropy-driven Sampling and Training Scheme for Conditional Diffusion Generation

Denoising Diffusion Probabilistic Model (DDPM) is able to make flexible ...

User-defined Event Sampling and Uncertainty Quantification in Diffusion Models for Physical Dynamical Systems

Diffusion models are a class of probabilistic generative models that hav...

Flow Plugin Network for conditional generation

Generative models have gained many researchers' attention in the last ye...

Please sign up or login with your details

Forgot password? Click here to reset