Representation Learning in Continuous-Time Score-Based Generative Models

Korbinian Abstreiter, Stefan Bauer, Arash Mehrjou

Keywords: representation learning, score-based, diffusion models, generative modeling

Abstract:

Score-based methods represented as stochastic differential equations on a continuous time domain have recently proven successful as a non-adversarial generative model.
Training such models relies on denoising score matching, which can be seen as multi-scale denoising autoencoders.
Here, we augment the denoising score-matching framework to enable representation learning without any supervised signal.
GANs and VAEs learn representations by directly transforming latent codes to data samples.
In contrast, score-based representation learning relies on a new formulation of the denoising score-matching objective and thus encodes information needed for denoising.
We show how this difference allows for manual control of the level of detail encoded in the representation.