arXiv subjects

Weiyi Gong

Publications and source records attributed to Weiyi Gong.

7 recordsLinked to original sources

arXiv2026

Materials design based on a material-motif network and heterogeneous graphs

Machine learning models for functional materials design require precise and informative representations of material systems. Common representations encode atomic composition and bonding but often do not include local coordination environments across chemically diverse crystals. Recurring structural motifs provide a motif level description of crystalline solids and can serve as interpretable descriptors for structure property learning. To analyze the motif connectivity in materials, we construct a bipartite material motif network from 131,548 Materials Project entries, with materials and motifs as the two node sets. Edges connect materials to their constituent motifs and are weighted by motif distortion, which quantifies the strength of each material motif association. Network connectivity is analyzed to identify motif-defined material clusters that capture recurring local geometries relevant to structure property trends. Most shared motifs act as hubs that connect otherwise disconnected regions of the network, enabling motif guided screening by expanding from known motifs to nearby materials in the same neighborhoods. A network embedding step converts this weighted connectivity into vector representations of materials. Using these motif informed embeddings, property prediction yields a formation energy mean absolute error (MAE) of 0.157 eV per atom and a bandgap MAE of 0.601 eV. These results indicate that motif connectivity provides a compact, interpretable representation that complements existing descriptors for scalable screening and structure property modeling.

cond-mat.mtrl-sci↗

arXiv2025

Graph Transformer Networks for Accurate Band Structure Prediction: An End-to-End Approach

Predicting electronic band structures from crystal structures is crucial for understanding structure-property correlations in materials science. First-principles approaches are accurate but computationally intensive. Recent years, machine learning (ML) has been extensively applied to this field, while existing ML models predominantly focus on band gap predictions or indirect band structure estimation via solving predicted Hamiltonians. An end-to-end model to predict band structure accurately and efficiently is still lacking. Here, we introduce a graph Transformer-based end-to-end approach that directly predicts band structures from crystal structures with high accuracy. Our method leverages the continuity of the k-path and treat continuous bands as a sequence. We demonstrate that our model not only provides accurate band structure predictions but also can derive other properties (such as band gap, band center, and band dispersion) with high accuracy. We verify the model performance on large and diverse datasets.

cond-mat.mtrl-sci↗

arXiv2024

Crystal Hypergraph Convolutional Networks

Graph representations of solid state materials that encode only interatomic distance lack geometrical resolution, resulting in degenerate representations that may map distinct structures to equivalent graphs. Here we propose a hypergraph representation scheme for materials that allows for the association of higher-order geometrical information with hyperedges. Hyperedges generalize edges to connected sets of more than two nodes, and may be used to represent triplets and local environments of atoms in materials. This generalization of edges requires a different approach in graph convolution, three of which are developed in this paper. Results presented here focus on the improved performance of models based on both pair-wise edges and local environment hyperedges. These results demonstrate that hypergraphs are an effective method for incorporating geometrical information in material representations.

cond-mat.mtrl-sci↗

arXiv2024

Symmetry-guided data-driven discovery of native quantum defects in two-dimensional materials

Drawing on their atomically thin structure, two-dimensional (2D) materials present a groundbreaking avenue for the precision fabrication and systematic manipulation of quantum defects. Through a method grounded in site-symmetry principles, we devise a comprehensive workflow to pinpoint potential native quantum defects across the entire spectrum of known binary 2D materials. Leveraging both symmetry principles and data-driven approaches markedly enhances the identification of spin defects exhibiting triplet ground states. This advancement is pivotal in discovering NV-like quantum defects in 2D materials, which are instrumental in facilitating a set of quantum functionalities. For discerning the multifaceted functionalities of these quantum defect candidates, their magneto-optical properties are comprehensively estimated using high-throughput computations. Our findings underscore that antisite defects in diverse hosts emerge as prospective quantum defects of significance. Crucially, based on our research, we advocate that the 16 antisites present in post-transition metal monochalcogenides (PTMCs) stand out as a prominent 2D-material-based quantum defect platforms, by their precise defect levels, optimal magneto-optical attributes, and the readily accessible nature of their host materials. This work substantially broadens the repertoire of quantum defects within the 2D material landscape, presenting profound implications for the advancement of quantum information science and technologies.

cond-mat.mtrl-sci↗

arXiv2024

Bridging deep learning force fields and electronic structures with a physics-informed approach

This work presents a physics-informed neural network approach bridging deep-learning force field and electronic structure simulations, illustrated through twisted two-dimensional large-scale material systems. The deep potential molecular dynamics model is adopted as the backbone, and electronic structure simulation is integrated. Using Wannier functions as the basis, we categorize Wannier Hamiltonian elements based on physical principles to incorporate diverse information from a deep-learning force field model. This information-sharing mechanism streamlines the architecture of our multifunctional model, enhancing its efficiency and effectiveness. Utilizing Wannier functions as the basis lays the groundwork for predicting more physical quantities. This approach serves as a powerful tool to explore both the structural and electronic properties of large-scale systems characterized by low periodicities. By endowing an existing well-developed machine-learning force field with electronic structure simulation capabilities, the study marks a significant advancement in developing multimodal machine-learning-based computational methods that can achieve multiple functionalities traditionally exclusive to first-principles calculations.

cond-mat.mtrl-sci↗

arXiv2022

Incorporation of density scaling constraint in density functional design via contrastive representation learning

In a data-driven paradigm, machine learning (ML) is the central component for developing accurate and universal exchange-correlation (XC) functionals in density functional theory (DFT). It is well known that XC functionals must satisfy several exact conditions and physical constraints, such as density scaling, spin scaling, and derivative discontinuity. In this work, we demonstrate that contrastive learning is a computationally efficient and flexible method to incorporate a physical constraint in ML-based density functional design. We propose a schematic approach to incorporate the uniform density scaling property of electron density for exchange energies by adopting contrastive representation learning during the pretraining task. The pretrained hidden representation is transferred to the downstream task to predict the exchange energies calculated by DFT. The electron density encoder transferred from the pretraining task based on contrastive learning predicts exchange energies that satisfy the scaling property, while the model trained without using contrastive learning gives poor predictions for the scaling-transformed electron density systems. Furthermore, the model with pretrained encoder gives a satisfactory performance with only small fractions of the whole augmented dataset labeled, comparable to the model trained from scratch using the whole dataset. The results demonstrate that incorporating exact constraints through contrastive learning can enhance the understanding of density-energy mapping using neural network (NN) models with less data labeling, which will be beneficial to generalizing the application of NN-based XC functionals in a wide range of scenarios that are not always available experimentally but theoretically justified. This work represents a viable pathway toward the machine learning design of a universal density functional via representation learning.

physics.chem-ph↗

arXiv2019

Intrinsic long range antiferromagnetic coupling in dilutely V doped CuInTe$_2$

Despite the various magnetic orders mediated by superexchange mechanism, the existence of a long range antiferromagnetic (AFM) coupling is unknown. Based on DFT calculations, we discovered an intrinsic long range AFM coupling in V doped CuInTe$_2$. The AFM coupling is mainly due to the $p-d$ coupling and electron redistribution along the interacting chains. The relatively small energy difference between $p$ and $d$ orbitals and the small energy difference between d orbitals of the dopants and that of stepping stone sites can enhance the stability of this AFM configuration. A multi-bands Hubbard model was proposed to provide fundamental understanding to the long range AFM coupling in chalcopyrite diluted magnetic semiconductors(DMS).

cond-mat.mtrl-sci↗