ComboStoc: Combinatorial Stochasticity for Diffusion Generative Models

Rui Xu, Jiepeng Wang, Hao Pan, Yang Liu, Xin Tong, Shiqing Xin, Changhe Tu, Taku Komura, Wenping Wang

Keywords: generative models, combinatorial, stochastic

TL;DR: We present combinatorial stochasticity for improving both training efficiency and generation capacity of diffusion generative models.

Abstract:

In this paper, we study an under-explored but important factor of diffusion generative models, i.e., the combinatorial complexity.
Data samples are generally high-dimensional, and for various structured generation tasks, additional attributes are combined to associate with data samples.
We show that the space spanned by the combination of dimensions and attributes is insufficiently sampled by existing training scheme of diffusion generative models, causing degraded test time performance.
We present a simple fix to this problem by constructing stochastic processes that fully exploit the combinatorial structures, hence the name ComboStoc.
Using this simple strategy, we show that network training is significantly accelerated across diverse data modalities, including images and 3D structured shapes.
Moreover, ComboStoc enables a new way of test time generation which uses asynchronous time steps for different dimensions and attributes, thus allowing for varying degrees of control over them.

Primary Area: generative models

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 5436