Structural Constraint Integration in Generative Model for Discovery of Quantum Material Candidates

• URL: http://arxiv.org/abs/2407.04557v1
• Date: Fri, 5 Jul 2024 14:42:54 GMT
• Title: Structural Constraint Integration in Generative Model for Discovery of Quantum Material Candidates
• Authors: Ryotaro Okabe, Mouyang Cheng, Abhijatmedhi Chotrattanapituk, Nguyen Tuan Hung, Xiang Fu, Bowen Han, Yao Wang, Weiwei Xie, Robert J. Cava, Tommi S. Jaakkola, Yongqiang Cheng, Mingda Li,
• Abstract summary: We introduce Structural Constraint Integration in the GENerative model (SCIGEN) We generate eight million compounds using Archimedean lattices as prototype constraints, with over 10% surviving a multi-staged stability pre-screening. Since the properties of quantum materials are closely related to geometric patterns, our results indicate that SCIGEN provides a general framework for generating quantum materials candidates.
• Score: 27.416978540039878
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Billions of organic molecules are known, but only a tiny fraction of the functional inorganic materials have been discovered, a particularly relevant problem to the community searching for new quantum materials. Recent advancements in machine-learning-based generative models, particularly diffusion models, show great promise for generating new, stable materials. However, integrating geometric patterns into materials generation remains a challenge. Here, we introduce Structural Constraint Integration in the GENerative model (SCIGEN). Our approach can modify any trained generative diffusion model by strategic masking of the denoised structure with a diffused constrained structure prior to each diffusion step to steer the generation toward constrained outputs. Furthermore, we mathematically prove that SCIGEN effectively performs conditional sampling from the original distribution, which is crucial for generating stable constrained materials. We generate eight million compounds using Archimedean lattices as prototype constraints, with over 10% surviving a multi-staged stability pre-screening. High-throughput density functional theory (DFT) on 26,000 survived compounds shows that over 50% passed structural optimization at the DFT level. Since the properties of quantum materials are closely related to geometric patterns, our results indicate that SCIGEN provides a general framework for generating quantum materials candidates.

Related papers

• DecompOpt: Controllable and Decomposed Diffusion Models for Structure-based Molecular Optimization [49.85944390503957]
  DecompOpt is a structure-based molecular optimization method based on a controllable and diffusion model. We show that DecompOpt can efficiently generate molecules with improved properties than strong de novo baselines.
  arXiv  Detail & Related papers  (2024-03-07T02:53:40Z)
• Spectroscopy-Guided Discovery of Three-Dimensional Structures of Disordered Materials with Diffusion Models [6.97950396242977]
  We introduce a new framework based on the diffusion model to predict 3D structures of disordered materials from a target property. We show that our model can steer the generative process to tailor atomic arrangements for a specific XANES spectrum. Our work represents a significant stride in bridging the gap between materials characterization and atomic structure determination.
  arXiv  Detail & Related papers  (2023-12-09T05:40:10Z)
• MatterGen: a generative model for inorganic materials design [20.119976243451216]
  We present MatterGen, a model that generates stable, diverse inorganic materials across the periodic table. Compared to prior generative models structures produced by MatterGen are more than twice as likely to be novel and stable. We demonstrate multi-property materials design capabilities by proposing structures that have both high magnetic density and a chemical composition with low supply-chain risk.
  arXiv  Detail & Related papers  (2023-12-06T18:52:16Z)
• Scalable Diffusion for Materials Generation [99.71001883652211]
  We develop a unified crystal representation that can represent any crystal structure (UniMat) UniMat can generate high fidelity crystal structures from larger and more complex chemical systems. We propose additional metrics for evaluating generative models of materials.
  arXiv  Detail & Related papers  (2023-10-18T15:49:39Z)
• Generative Hyperelasticity with Physics-Informed Probabilistic Diffusion Fields [0.0]
  Data-driven strain energy functions possess the flexibility to capture the behavior of complex materials. We leverage recent advances in generative models to create realistic hyperelastic material models. We extend our approach to spatially correlated diffusion in heterogeneous material properties for arbitrary geometries.
  arXiv  Detail & Related papers  (2023-09-11T19:35:23Z)
• 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)
• Latent Diffusion Energy-Based Model for Interpretable Text Modeling [104.85356157724372]
  We introduce a novel symbiosis between the diffusion models and latent space EBMs in a variational learning framework. We develop a geometric clustering-based regularization jointly with the information bottleneck to further improve the quality of the learned latent space.
  arXiv  Detail & Related papers  (2022-06-13T03:41:31Z)
• Physics Guided Generative Adversarial Networks for Generations of Crystal Materials with Symmetry Constraints [9.755053639966185]
  We propose a Physics Guided Crystal Generative Model (PGCGM) for new materials generation. By augmenting the base atom sites of materials, our model can generate new materials of 20 space groups. Our method increases the generator's validity by 8 times compared to one of the baselines.
  arXiv  Detail & Related papers  (2022-03-27T17:21:36Z)
• Moser Flow: Divergence-based Generative Modeling on Manifolds [49.04974733536027]
  Moser Flow (MF) is a new class of generative models within the family of continuous normalizing flows (CNF) MF does not require invoking or backpropagating through an ODE solver during training. We demonstrate for the first time the use of flow models for sampling from general curved surfaces.
  arXiv  Detail & Related papers  (2021-08-18T09:00:24Z)
• BIGDML: Towards Exact Machine Learning Force Fields for Materials [55.944221055171276]
  Machine-learning force fields (MLFF) should be accurate, computationally and data efficient, and applicable to molecules, materials, and interfaces thereof. Here, we introduce the Bravais-Inspired Gradient-Domain Machine Learning approach and demonstrate its ability to construct reliable force fields using a training set with just 10-200 atoms.
  arXiv  Detail & Related papers  (2021-06-08T10:14:57Z)

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.