Kolmogorov-Arnold graph neural networks for chemically informed prediction tasks on inorganic nanomaterials

TL;DR

This paper introduces Kolmogorov-Arnold graph neural networks (KAGNNs) tailored for inorganic nanomaterials, demonstrating their superior performance over existing GNNs on large-scale inorganic datasets, especially in crystal classification tasks.

Contribution

The study adapts KAGNNs for inorganic nanomaterials and achieves state-of-the-art results on the CHILI dataset, extending their application beyond organic molecules.

Findings

KAGNNs outperform traditional GNNs on inorganic datasets.

Achieved 99.5% accuracy in crystal system classification.

Achieved 96.6% accuracy in space group classification.

Abstract

The recent development of Kolmogorov-Arnold Networks (KANs) has found its application in the field of Graph Neural Networks (GNNs) particularly in molecular data modeling and potential drug discovery. Kolmogorov-Arnold Graph Neural Networks (KAGNNs) expand on the existing set of GNN models with KAN-based counterparts. KAGNNs have been demonstrably successful in surpassing the accuracy of MultiLayer Perceptron (MLP)-based GNNs in the task of molecular property prediction. These models were widely tested on the graph datasets consisting of organic molecules. In this study, we explore the application of KAGNNs towards inorganic nanomaterials. In 2024, a large scale inorganic nanomaterials dataset was published under the title CHILI (Chemically-Informed Large-scale Inorganic Nanomaterials Dataset), and various MLP-based GNNs have been tested on this dataset. We adapt and test our own KAGNNs appropriate for eight defined tasks. Our experiments reveal that, KAGNNs frequently surpass the performance of their counterpart GNNs. Most notably, on crystal system and space group classification tasks in CHILI-3K, KAGNNs achieve the new state-of-the-art results of 99.5 percent and 96.6 percent accuracy, respectively, compared to the previous 65.7 and 73.3 percent each.