On Accelerating Diffusion-based Molecular Conformation Generation in SE(3)-invariant Space

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhou, Zihan, Liu, Ruiying, Yu, Tianshu
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911768622661632
author Zhou, Zihan
Liu, Ruiying
Yu, Tianshu
author_facet Zhou, Zihan
Liu, Ruiying
Yu, Tianshu
contents Diffusion-based generative models in SE(3)-invariant space have demonstrated promising performance in molecular conformation generation, but typically require solving stochastic differential equations (SDEs) with thousands of update steps. Till now, it remains unclear how to effectively accelerate this procedure explicitly in SE(3)-invariant space, which greatly hinders its wide application in the real world. In this paper, we systematically study the diffusion mechanism in SE(3)-invariant space via the lens of approximate errors induced by existing methods. Thereby, we develop more precise approximate in SE(3) in the context of projected differential equations. Theoretical analysis is further provided as well as empirical proof relating hyper-parameters with such errors. Altogether, we propose a novel acceleration scheme for generating molecular conformations in SE(3)-invariant space. Experimentally, our scheme can generate high-quality conformations with 50x--100x speedup compared to existing methods.
format Preprint
id arxiv_https___arxiv_org_abs_2310_04915
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle On Accelerating Diffusion-based Molecular Conformation Generation in SE(3)-invariant Space
Zhou, Zihan
Liu, Ruiying
Yu, Tianshu
Computational Physics
Artificial Intelligence
Machine Learning
Diffusion-based generative models in SE(3)-invariant space have demonstrated promising performance in molecular conformation generation, but typically require solving stochastic differential equations (SDEs) with thousands of update steps. Till now, it remains unclear how to effectively accelerate this procedure explicitly in SE(3)-invariant space, which greatly hinders its wide application in the real world. In this paper, we systematically study the diffusion mechanism in SE(3)-invariant space via the lens of approximate errors induced by existing methods. Thereby, we develop more precise approximate in SE(3) in the context of projected differential equations. Theoretical analysis is further provided as well as empirical proof relating hyper-parameters with such errors. Altogether, we propose a novel acceleration scheme for generating molecular conformations in SE(3)-invariant space. Experimentally, our scheme can generate high-quality conformations with 50x--100x speedup compared to existing methods.
title On Accelerating Diffusion-based Molecular Conformation Generation in SE(3)-invariant Space
topic Computational Physics
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2310.04915