Do Graph Neural Networks Work for High Entropy Alloys?

Hengrui Zhang, Ruishu Huang, Jie Chen, James M. Rondinelli, Wei Chen
8/29/2024
cs.LGcond-mat.mtrl-sci

No official code found. Best implementation: Henrium/LESets (9 stars, MIT, last commit 2025-04-04).

Abstract

Graph neural networks (GNNs) have excelled in predictive modeling for both crystals and molecules, owing to the expressiveness of graph representations. High-entropy alloys (HEAs), however, lack chemical long-range order, limiting the applicability of current graph representations. To overcome this challenge, we propose a representation of HEAs as a collection of local environment (LE) graphs. Based on this representation, we introduce the LESets machine learning model, an accurate, interpretable GNN for HEA property prediction. We demonstrate the accuracy of LESets in modeling the mechanical properties of quaternary HEAs. Through analyses and interpretation, we further extract insights into the modeling and design of HEAs. In a broader sense, LESets extends the potential applicability of GNNs to disordered materials with combinatorial complexity formed by diverse constituents and their flexible configurations.

View on arXivView PDF

Code Implementations(1)

Henrium/LESetsCommunity100%
MIT

A graph neural network for high-entropy alloys.

91Python, Jupyter NotebookAug 30, 20241 years agoMIT
graph-neural-networkgraph-representationhigh-entropy-alloy

Similar Papers

Graph neural network framework for energy mapping of hybrid monte-carlo molecular dynamics simulations of Medium Entropy Alloys

90% match2024

DenseGNN: universal and scalable deeper graph neural networks for high-performance property prediction in crystals and molecules

85% match1 repo302025

Enhancing material property prediction with ensemble deep graph convolutional networks

83% match2024

Substitutional Alloying Using Crystal Graph Neural Networks

83% match2023

CrysGNN : Distilling pre-trained knowledge to enhance property prediction for crystalline materials

83% match1 repo312023

CrysAtom: Distributed Representation of Atoms for Crystal Property Prediction

83% match1 repo12024

Cite this paper

@article{zhang2024graph,
  title  = {Do Graph Neural Networks Work for High Entropy Alloys?},
  author = {Hengrui Zhang and Ruishu Huang and Jie Chen and James M. Rondinelli and Wei Chen},
  year   = {2024},
  eprint = {2408.16337},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2408.16337v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2408.16337.svg)](https://codeofpaper.com/paper/2408.16337)

Discussion