Material Property Prediction using Graphs based on Generically Complete Isometry Invariants

• URL: http://arxiv.org/abs/2212.11246v3
• Date: Tue, 7 May 2024 13:41:58 GMT
• Title: Material Property Prediction using Graphs based on Generically Complete Isometry Invariants
• Authors: Jonathan Balasingham, Viktor Zamaraev, Vitaliy Kurlin,
• Abstract summary: This work adapts the Pointwise Distance Distribution for a simpler graph whose vertices set is not larger than the asymmetric unit of a crystal structure. The Distribution Graph reduces mean-absolute-error by 0.6%-12% while having 44%-88% of the number of vertices when compared to the crystal graph.
• Score: 3.031375888004876
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The structure-property hypothesis says that the properties of all materials are determined by an underlying crystal structure. The main obstacle was the ambiguity of conventional crystal representations based on incomplete or discontinuous descriptors that allow false negatives or false positives. This ambiguity was resolved by the ultra-fast Pointwise Distance Distribution (PDD), which distinguished all periodic structures in the world's largest collection of real materials (Cambridge Structural Database). The state-of-the-art results in property predictions were previously achieved by graph neural networks based on various graph representations of periodic crystals, including the Crystal Graph with vertices at all atoms in a crystal unit cell. This work adapts the Pointwise Distance Distribution for a simpler graph whose vertex set is not larger than the asymmetric unit of a crystal structure. The new Distribution Graph reduces mean-absolute-error by 0.6\%-12\% while having 44\%-88\% of the number of vertices when compared to the crystal graph when applied on the Materials Project and Jarvis-DFT datasets using CGCNN and ALIGNN. Methods for hyper-parameters selection for the graph are backed by the theoretical results of the Pointwise Distance Distribution and are then experimentally justified.

Related papers

• Generalization of Geometric Graph Neural Networks [84.01980526069075]
  We study the generalization capabilities of geometric graph neural networks (GNNs) We prove a generalization gap between the optimal empirical risk and the optimal statistical risk of this GNN. The most important observation is that the generalization capability can be realized with one large graph instead of being limited to the size of the graph as in previous results.
  arXiv  Detail & Related papers  (2024-09-08T18:55:57Z)
• PDDFormer: Pairwise Distance Distribution Graph Transformer for Crystal Material Property Prediction [8.36720478795747]
  We propose the atom-Weighted Pairwise Distance Distribution (WPDD) and Unit cell Pairwise Distance Distribution (UPDD) for the first time, incorporating them into the construction of multi-edge crystal graphs. We demonstrate that this method maintains the continuity and completeness of crystal graphs even under slight perturbations in atomic positions.
  arXiv  Detail & Related papers  (2024-08-23T11:05:48Z)
• CrysToGraph: A Comprehensive Predictive Model for Crystal Materials Properties and the Benchmark [16.456990796982186]
  We propose CrysToGraph ($textbfCrys$tals with $textbfT$ransformers $textbfo$n $textbfGraph$s), a novel transformer-based graph geometric network designed specifically for unconventional crystalline systems. CrysToGraph effectively captures short-range interactions with transformer-based graph convolution blocks as well as long-range interactions with graph-wise transformer blocks. It outperforms most existing methods, achieving new state-of-the-art results on the benchmarks of both unconventional crystals and traditional crystals
  arXiv  Detail & Related papers  (2024-07-23T02:31:06Z)
• Complete and Efficient Graph Transformers for Crystal Material Property Prediction [53.32754046881189]
  Crystal structures are characterized by atomic bases within a primitive unit cell that repeats along a regular lattice throughout 3D space. We introduce a novel approach that utilizes the periodic patterns of unit cells to establish the lattice-based representation for each atom. We propose ComFormer, a SE(3) transformer designed specifically for crystalline materials.
  arXiv  Detail & Related papers  (2024-03-18T15:06:37Z)
• Graph Generation via Spectral Diffusion [51.60814773299899]
  We present GRASP, a novel graph generative model based on 1) the spectral decomposition of the graph Laplacian matrix and 2) a diffusion process. Specifically, we propose to use a denoising model to sample eigenvectors and eigenvalues from which we can reconstruct the graph Laplacian and adjacency matrix. Our permutation invariant model can also handle node features by concatenating them to the eigenvectors of each node.
  arXiv  Detail & Related papers  (2024-02-29T09:26:46Z)
• PerCNet: Periodic Complete Representation for Crystal Graphs [3.7050297294650716]
  A reasonable crystal representation method should capture the local and global information. We propose a periodic complete representation and calculation algorithm for infinite extended crystal materials. Based on the proposed representation, we then propose a network for predicting crystal material properties, PerCNet.
  arXiv  Detail & Related papers  (2023-12-03T08:55:35Z)
• Graph Out-of-Distribution Generalization with Controllable Data Augmentation [51.17476258673232]
  Graph Neural Network (GNN) has demonstrated extraordinary performance in classifying graph properties. Due to the selection bias of training and testing data, distribution deviation is widespread. We propose OOD calibration to measure the distribution deviation of virtual samples.
  arXiv  Detail & Related papers  (2023-08-16T13:10:27Z)
• From Spectrum Wavelet to Vertex Propagation: Graph Convolutional Networks Based on Taylor Approximation [85.47548256308515]
  Graph convolutional networks (GCN) have been recently utilized to extract the underlying structures of datasets with some labeled data and high-dimensional features. Existing GCNs mostly rely on a first-order Chebyshev approximation of graph wavelet- Kernels.
  arXiv  Detail & Related papers  (2020-07-01T20:07:13Z)
• Convergence and Stability of Graph Convolutional Networks on Large Random Graphs [22.387735135790706]
  We study properties of Graph Convolutional Networks (GCNs) by analyzing their behavior on standard models of random graphs. We first study the convergence of GCNs to their continuous counterpart as the number of nodes grows. We then analyze the stability of GCNs to small deformations of the random graph model.
  arXiv  Detail & Related papers  (2020-06-02T18:36:19Z)
• Block-Approximated Exponential Random Graphs [77.4792558024487]
  An important challenge in the field of exponential random graphs (ERGs) is the fitting of non-trivial ERGs on large graphs. We propose an approximative framework to such non-trivial ERGs that result in dyadic independence (i.e., edge independent) distributions. Our methods are scalable to sparse graphs consisting of millions of nodes.
  arXiv  Detail & Related papers  (2020-02-14T11:42:16Z)

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.