High-entropy perovskite oxides (HEPOs) represent a chemically complex class of materials with promising functional properties, yet their vast compositional space and, chemical/structural disorder pose significant challenge for accurate property prediction. Graph neural networks (GNNs) enable rapid exploration of materials space but are often limited by the availability of representative training data. Here, we investigate ordered-to-disordered transfer learning using GNNs for formation-energy and HOMO-LUMO gap prediction in HEPOs by transferring knowledge learned from chemically ordered perovskites. Four representative GNN models, including CGCNN, GATGNN, ALIGNN and M3GNet are evaluated to understand the role of structural representations, spanning pairwise two-body and angular three-body interactions in transfer performance. We find strong property-dependent transfer behavior: formation-energy prediction transfers effectively to disordered HEPOs, whereas HOMO-LUMO gap prediction shows limited transferability due to its sensitivity to local chemical environments. Incorporating a small HEPO-specific training dataset substantially improves HOMO-LUMO gap prediction. Representation-level analysis using UMAP further highlights the importance of encoding three-body geometric information such as in ALIGNN for capturing complex structure-property relationships and improving transferability.
Stacked bilayer materials exhibit rich stacking-dependent properties driven by the interplay between strong intra-layer bonding and weak inter-layer van der Waals interactions. The computational discovery of such materials is challenging because accurate structure generation typically relies on expensive DFT-based optimization, while existing machine-learning models often fail to explicitly distinguish different interaction types during property prediction. To address these challenges, we propose a machine-learning framework for efficient construction and property prediction of stacked bilayer materials. The framework employs a MatterSim-D3-based structural optimization workflow to generate DFT-quality bilayer structures from monolayer building blocks and stacking configurations at substantially reduced computational cost. For property prediction, we introduce BDIP-Net (Bilayer Dual-Interaction Potential Network), a graph neural network that explicitly models intra-layer and inter-layer interactions through interaction-specific potential representations and adaptive message fusion. We evaluate the proposed framework on BiDB, HetDB, and SAMBA, encompassing homobilayers, heterobilayers, and twisted bilayer systems. Results show that the MatterSim-D3-based workflow closely reproduces DFT-PBE-D3 optimized structures, while BDIP-Net consistently outperforms existing graph neural network and potential-based approaches for bilayer property prediction.
Anh Vuong, Chen Zhao, JinKang Hu et al.· 0 citations
Graph neural networks (GNNs) for crystal property prediction are typically evaluated by a single aggregate error, which can mask where, and for which classes of materials, these models fail. In this study, we present a space-group-, centering-type-, and band gap-resolved error analysis of GNN band gap prediction on the Materials Project dataset. As a channel for this analysis we use Crystal-X, a deliberately simple model: a standard graph convolutional backbone with two minor architectural modifications, an asymmetric edge convolution and a neighbor-feature transformation, that supplement bond information often treated as secondary in node-centric models. Crystal-X is not a state-of-the-art model: it reaches a band gap MAE of 0.256 eV on the MP 2018.6 dataset, behind ALIGNN (0.22 eV) and PotNet (0.20 eV), though ahead of older baselines such as CGCNN (0.39 eV), SchNet (0.415 eV), and MEGNet (0.33 eV) while using only the nine-property CGCNN atomic feature set. Its value here is as a controlled, low-complexity testbed for the error analysis. That analysis reveals systematic patterns that aggregate MAE conceals: errors concentrate in underrepresented band gap ranges and in low-symmetry and non-centrosymmetric space groups; per-group errors for sparsely populated space groups are dominated by sampling noise; and modest, as-yet-unverified gains from edge-aware convolutions appear in monoclinic and non-primitive-centered systems. We argue that this kind of granular, symmetry-resolved evaluation should accompany aggregate benchmarks when assessing crystal GNNs.
Shehroz A. Shoaib, Burhan K. SaifAddin· Crystals· 0 citations
A semiempirical extended tight-binding approach (GFN1-xTB) is employed to compute the electronic properties of a dataset of MOFs, and it is shown that GFN1-xTB approximates MOF band gaps well, as compared to semilocal DFT.
A. Jose, A. Walsh· Journal of Chemical Theory a...· 0 citations
This work combined ab initio optical-property calculations with a tabular foundation-model regression to predict the real and imaginary components of the frequency-dependent dielectric function for Mo-W-S-Se-Te TMD alloys, and predicted derived optical quantities, including refractive index, extinction coefficient, and absorption coefficient.
Vivek Chowdhury, Tarvir Anjum Aditto, M. Samrat et al.· 0 citations
A structure-aware graph neural network is trained to predict cross-functional energy residuals and align inconsistent DFT energy scales, which enables reliable predictions of phase stability, battery voltage profiles, and reaction thermodynamics, while allowing the integration of multi-source DFT data to advance the development of high-performance materials foundation models.
Yidong Huang, Tenglong Lu, Hanwen Kang et al.· 0 citations
Predicting the structure-dependent dielectric responses of high-k oxides remains a fundamental bottleneck in the development of next-generation nanoelectronics, primarily due to the complex nature of ionic polarization. In this work, we propose a physics-informed hybrid framework designed for the performance prediction of these materials. We explicitly decouple the total dielectric constant into its electronic (εel) and ionic (εion) contributions. To capture the multi-body interactions and bond-angle distortions that govern εion, we employ the Atomistic Line Graph Neural Network (ALIGNN). Crucially, the extracted structure-aware representations are coupled with a pre-training strategy and refined via an XGBoost ensemble regressor within a stacking architecture. This approach achieves high predictive accuracy, yielding an R2 of 0.943 for εel and 0.791 for the inherently challenging εion. Furthermore, it reduces the log-domain mean absolute error (MAE) of the total dielectric constant to 0.073, corresponding to a physical-domain MAE of ≈2.9, demonstrating improvements over both pure tree-based baselines and vanilla graph networks. Deploying this framework for high-throughput screening, we evaluated candidate oxides against stringent criteria, including a wide bandgap threshold Eg > 4.0 eV to suppress leakage currents. The pipeline successfully identified three promising high-k candidates, (Sr3Hf2O7, SrHfO3, Li2HfO3) offering a physically interpretable and scalable route for data-driven performance predictions of advanced electronic materials.
