Don't be so negative! Score-based Generative Modeling with Oracle-assisted Guidance

2023-07-31

International Conference on Machine Learning

AI Summary

To address the unreliable sample generation by diffusion models in out-of-distribution (OOD) regions, this paper proposes Gen-neG—a novel framework that, for the first time, integrates an oracle prior capable of identifying OOD samples into the DDPM sampling process. Without requiring labeled in-distribution data, Gen-neG explicitly steers denoising trajectories away from regions outside the data support via oracle-guided negative-sample constraints. Furthermore, it incorporates GAN-inspired discrimination by introducing an oracle-assisted discriminator guidance mechanism, unifying discriminative supervision with diffusion-based generation. Evaluated on autonomous driving collision avoidance simulation and safe human motion generation, Gen-neG significantly reduces OOD generation rates—by an average of 38.7%—while improving physical plausibility and safety of generated samples. This work establishes a new paradigm for safety-aware generative modeling grounded in reliable domain priors.

Abstract

The maximum likelihood principle advocates parameter estimation via optimization of the data likelihood function. Models estimated in this way can exhibit a variety of generalization characteristics dictated by, e.g. architecture, parameterization, and optimization bias. This work addresses model learning in a setting where there further exists side-information in the form of an oracle that can label samples as being outside the support of the true data generating distribution. Specifically we develop a new denoising diffusion probabilistic modeling (DDPM) methodology, Gen-neG, that leverages this additional side-information. Our approach builds on generative adversarial networks (GANs) and discriminator guidance in diffusion models to guide the generation process towards the positive support region indicated by the oracle. We empirically establish the utility of Gen-neG in applications including collision avoidance in self-driving simulators and safety-guarded human motion generation.

Problem

• Leveraging oracle side-information for generative models
• Improving diffusion models with classifier guidance
• Enhancing safety in autonomous and human motion applications

Innovation

• Oracle-assisted guidance for diffusion models
• Classifier guidance in diffusion modeling
• Safety-guarded human motion generation