Open Materials Generation with Stochastic Interpolants

• URL: http://arxiv.org/abs/2502.02582v1
• Date: Tue, 04 Feb 2025 18:56:47 GMT
• Title: Open Materials Generation with Stochastic Interpolants
• Authors: Philipp Hoellmer, Thomas Egg, Maya M. Martirossyan, Eric Fuemmeler, Amit Gupta, Zeren Shui, Pawan Prakash, Adrian Roitberg, Mingjie Liu, George Karypis, Mark Transtrum, Richard G. Hennig, Ellad B. Tadmor, Stefano Martiniani,
• Abstract summary: We introduce Open Materials Generation (OMG), a unifying framework for the generative design and discovery of crystalline materials. OMG employs inorganic interpolants (SI) to bridge an arbitrary base distribution to the target distribution of crystals. We benchmark OMG's performance on two tasks: Crystal Structure Prediction (CSP) for specified compositions, and 'de novo' generation (DNG) aimed at discovering stable, novel, and unique structures.
• Score: 14.939468363546384
• License:
• Abstract: The discovery of new materials is essential for enabling technological advancements. Computational approaches for predicting novel materials must effectively learn the manifold of stable crystal structures within an infinite design space. We introduce Open Materials Generation (OMG), a unifying framework for the generative design and discovery of inorganic crystalline materials. OMG employs stochastic interpolants (SI) to bridge an arbitrary base distribution to the target distribution of inorganic crystals via a broad class of tunable stochastic processes, encompassing both diffusion models and flow matching as special cases. In this work, we adapt the SI framework by integrating an equivariant graph representation of crystal structures and extending it to account for periodic boundary conditions in unit cell representations. Additionally, we couple the SI flow over spatial coordinates and lattice vectors with discrete flow matching for atomic species. We benchmark OMG's performance on two tasks: Crystal Structure Prediction (CSP) for specified compositions, and 'de novo' generation (DNG) aimed at discovering stable, novel, and unique structures. In our ground-up implementation of OMG, we refine and extend both CSP and DNG metrics compared to previous works. OMG establishes a new state-of-the-art in generative modeling for materials discovery, outperforming purely flow-based and diffusion-based implementations. These results underscore the importance of designing flexible deep learning frameworks to accelerate progress in materials science.

Related papers

• DiffMS: Diffusion Generation of Molecules Conditioned on Mass Spectra [60.39311767532607]
  DiffMS is a formula-restricted encoder-decoder generative network. We develop a robust decoder that bridges latent embeddings and molecular structures. Experiments show DiffMS outperforms existing models on $textitde novo$ molecule generation.
  arXiv  Detail & Related papers  (2025-02-13T18:29:48Z)
• Efficient Symmetry-Aware Materials Generation via Hierarchical Generative Flow Networks [52.13486402193811]
  New solid-state materials require rapidly exploring the vast space of crystal structures and locating stable regions. Existing methods struggle to explore large material spaces and generate diverse samples with desired properties and requirements. We propose a novel generative model employing a hierarchical exploration strategy to efficiently exploit the symmetry of the materials space to generate crystal structures given desired properties.
  arXiv  Detail & Related papers  (2024-11-06T23:53:34Z)
• Structural Constraint Integration in Generative Model for Discovery of Quantum Material Candidates [27.416978540039878]
  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.
  arXiv  Detail & Related papers  (2024-07-05T14:42:54Z)
• FlowMM: Generating Materials with Riemannian Flow Matching [16.68310253042657]
  We present FlowMM, a pair of generative models that achieve state-of-the-art performance on both tasks. Our framework enables the freedom to choose the flow base distributions, drastically simplifying the problem of learning crystal structures. In addition to standard benchmarks, we validate FlowMM's generated structures with quantum chemistry calculations.
  arXiv  Detail & Related papers  (2024-06-07T07:46:23Z)
• 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)
• 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)
• Data-Driven Score-Based Models for Generating Stable Structures with Adaptive Crystal Cells [1.515687944002438]
  This work aims at the generation of new crystal structures with desired properties, such as chemical stability and specified chemical composition. The novelty of the presented approach resides in the fact that the lattice of the crystal cell is not fixed. A multigraph crystal representation is introduced that respects symmetry constraints, yielding computational advantages.
  arXiv  Detail & Related papers  (2023-10-16T02:53:24Z)
• FAENet: Frame Averaging Equivariant GNN for Materials Modeling [123.19473575281357]
  We introduce a flexible framework relying on frameaveraging (SFA) to make any model E(3)-equivariant or invariant through data transformations. We prove the validity of our method theoretically and empirically demonstrate its superior accuracy and computational scalability in materials modeling.
  arXiv  Detail & Related papers  (2023-04-28T21:48:31Z)
• How to See Hidden Patterns in Metamaterials with Interpretable Machine Learning [82.67551367327634]
  We develop a new interpretable, multi-resolution machine learning framework for finding patterns in the unit-cells of materials. Specifically, we propose two new interpretable representations of metamaterials, called shape-frequency features and unit-cell templates.
  arXiv  Detail & Related papers  (2021-11-10T21:19:02Z)

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.