Equivariant Diffusion for Crystal Structure Prediction

• URL: http://arxiv.org/abs/2512.07289v1
• Date: Mon, 08 Dec 2025 08:28:22 GMT
• Title: Equivariant Diffusion for Crystal Structure Prediction
• Authors: Peijia Lin, Pin Chen, Rui Jiao, Qing Mo, Jianhuan Cen, Wenbing Huang, Yang Liu, Dan Huang, Yutong Lu,
• Abstract summary: We propose EquiCSP, a novel equivariant diffusion-based generative model.<n>We develop a unique noising algorithm that rigorously maintains periodic translation equivariance throughout both training and inference processes.<n>Our experiments indicate that EquiCSP significantly surpasses existing models in terms of generating accurate structures.
• Score: 28.98416301694051
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In addressing the challenge of Crystal Structure Prediction (CSP), symmetry-aware deep learning models, particularly diffusion models, have been extensively studied, which treat CSP as a conditional generation task. However, ensuring permutation, rotation, and periodic translation equivariance during diffusion process remains incompletely addressed. In this work, we propose EquiCSP, a novel equivariant diffusion-based generative model. We not only address the overlooked issue of lattice permutation equivariance in existing models, but also develop a unique noising algorithm that rigorously maintains periodic translation equivariance throughout both training and inference processes. Our experiments indicate that EquiCSP significantly surpasses existing models in terms of generating accurate structures and demonstrates faster convergence during the training process.

Related papers

• Rethinking Diffusion Models with Symmetries through Canonicalization with Applications to Molecular Graph Generation [56.361076943802594]
  CanonFlow achieves state-of-the-art performance on the challenging GEOM-DRUG dataset, and the advantage remains large in few-step generation.
  arXiv  Detail & Related papers  (2026-02-16T18:58:55Z)
• Unlocking hidden biomolecular conformational landscapes in diffusion models at inference time [0.828988908878327]
  We present ConforMix, an inference-time algorithm that enhances sampling of conformational distributions.<n>Our approach upgrades diffusion models to enable more efficient discovery of conformational variability.<n>Case studies of biologically critical proteins demonstrate the scalability, accuracy, and utility of this method.
  arXiv  Detail & Related papers  (2025-12-02T23:52:05Z)
• Overcoming Dimensional Factorization Limits in Discrete Diffusion Models through Quantum Joint Distribution Learning [79.65014491424151]
  We propose a quantum Discrete Denoising Diffusion Probabilistic Model (QD3PM)<n>It enables joint probability learning through diffusion and denoising in exponentially large Hilbert spaces.<n>This paper establishes a new theoretical paradigm in generative models by leveraging the quantum advantage in joint distribution learning.
  arXiv  Detail & Related papers  (2025-05-08T11:48:21Z)
• Rao-Blackwell Gradient Estimators for Equivariant Denoising Diffusion [55.95767828747407]
  In domains such as molecular and protein generation, physical systems exhibit inherent symmetries that are critical to model.<n>We present a framework that reduces training variance and provides a provably lower-variance gradient estimator.<n>We also present a practical implementation of this estimator incorporating the loss and sampling procedure through a method we call Orbit Diffusion.
  arXiv  Detail & Related papers  (2025-02-14T03:26:57Z)
• A Periodic Bayesian Flow for Material Generation [20.62877413439857]
  We introduce CrysBFN, a novel crystal generation method by proposing a periodic Bayesian flow.<n>To successfully realize the concept of periodic Bayesian flow, CrysBFN integrates a new entropy conditioning mechanism.<n>Experiments over both crystal ab initio generation and crystal structure prediction tasks demonstrate the superiority of CrysBFN.
  arXiv  Detail & Related papers  (2025-02-04T05:07:13Z)
• Symmetry-Aware Generative Modeling through Learned Canonicalization [20.978208085043455]
  Generative modeling of symmetric densities has a range of applications in AI for science, from drug discovery to physics simulations.<n>We propose to model a learned slice of the density so that only one representative element per orbit is learned.<n>Preliminary experimental results on molecular modeling are promising, demonstrating improved sample quality and faster inference time.
  arXiv  Detail & Related papers  (2025-01-14T01:08:15Z)
• Conditional Synthesis of 3D Molecules with Time Correction Sampler [58.0834973489875]
  Time-Aware Conditional Synthesis (TACS) is a novel approach to conditional generation on diffusion models. It integrates adaptively controlled plug-and-play "online" guidance into a diffusion model, driving samples toward the desired properties.
  arXiv  Detail & Related papers  (2024-11-01T12:59:25Z)
• Broadening Target Distributions for Accelerated Diffusion Models via a Novel Analysis Approach [49.97755400231656]
  We show that a new accelerated DDPM sampler achieves accelerated performance for three broad distribution classes not considered before.<n>Our results show an improved dependency on the data dimension $d$ among accelerated DDPM type samplers.
  arXiv  Detail & Related papers  (2024-02-21T16:11:47Z)
• Convergence Analysis of Discrete Diffusion Model: Exact Implementation through Uniformization [17.535229185525353]
  We introduce an algorithm leveraging the uniformization of continuous Markov chains, implementing transitions on random time points. Our results align with state-of-the-art achievements for diffusion models in $mathbbRd$ and further underscore the advantages of discrete diffusion models in comparison to the $mathbbRd$ setting.
  arXiv  Detail & Related papers  (2024-02-12T22:26:52Z)
• Crystal Structure Prediction by Joint Equivariant Diffusion [27.52168842448489]
  Crystal Structure Prediction (CSP) is crucial in various scientific disciplines. This paper proposes DiffCSP, a novel diffusion model to learn the structure distribution from stable crystals.
  arXiv  Detail & Related papers  (2023-07-30T15:46:33Z)
• Geometric Neural Diffusion Processes [55.891428654434634]
  We extend the framework of diffusion models to incorporate a series of geometric priors in infinite-dimension modelling. We show that with these conditions, the generative functional model admits the same symmetry.
  arXiv  Detail & Related papers  (2023-07-11T16:51:38Z)
• GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation [102.85440102147267]
  We propose a novel generative model named GeoDiff for molecular conformation prediction. We show that GeoDiff is superior or comparable to existing state-of-the-art approaches.
  arXiv  Detail & Related papers  (2022-03-06T09:47:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.