Shaping Inductive Bias in Diffusion Models through Frequency-Based Noise Control
This work addresses the problem of improving generative performance in diffusion models for researchers and practitioners working with topologically structured data.
The authors tackled the problem of shaping inductive bias in diffusion models and achieved increased generative performance through frequency-based noise control, with notable improvements in image corruption and recovery tasks. The approach allows diffusion models to focus on particular aspects of the distribution to learn.
Diffusion Probabilistic Models (DPMs) are powerful generative models that have achieved unparalleled success in a number of generative tasks. In this work, we aim to build inductive biases into the training and sampling of diffusion models to better accommodate the target distribution of the data to model. For topologically structured data, we devise a frequency-based noising operator to purposefully manipulate, and set, these inductive biases. We first show that appropriate manipulations of the noising forward process can lead DPMs to focus on particular aspects of the distribution to learn. We show that different datasets necessitate different inductive biases, and that appropriate frequency-based noise control induces increased generative performance compared to standard diffusion. Finally, we demonstrate the possibility of ignoring information at particular frequencies while learning. We show this in an image corruption and recovery task, where we train a DPM to recover the original target distribution after severe noise corruption.