Disentangled Compositional Diffusion for Controllable Scientific Data Generation

Nandan Madhuj, Meet Hemant Parikh, Anirban Samaddar, Yixuan Sun, Sandeep Madireddy, Jian-Xun Wang

Keywords: Decomposed diffusion, Scientific Machine Learning, Controlled Generation

TL;DR: We demonstrate interpretable and controllable generation for scientific data through decomposed diffusion models using disentangled latent representation that can also be used for downstream scientific tasks.

Abstract: Diffusion and flow-based generative models are capable of generating high quality samples, but their internal representation is difficult to manipulate for controllable and interpretable generation, particularly for scientific applications. We employ decomposed diffusion models, which encode data into a latent representation, enabling interpretability by disentangling individual components and controllability by selecting components with desired features to generate new samples. We demonstrate applications on different datasets, including interpretability and controlled generation on temperature fields and vortex-induced flow fields, synthesizing human aortic geometries from very few samples, and 2D turbulent flow fields.

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 50