arXiv cs.AI· Gyoung S. Na·· 12 小时前AI 评分18
学习化学系统中异质子结构间的图间交互
Learning Inter-Graph Interactions Between Heterogeneous Substructures of Chemical Systems
AI 导读
研究提出一种面向复杂化学系统的数据描述符与图神经网络，用于学习有机与无机化合物之间的异质图间交互。将该方法用于预测含异质子结构的混合太阳能电池材料物理性质，在 1,682 种混合太阳能电池材料的带隙预测上达到 SOTA 精度。
正文 · 原文
Abstract:Complex chemical systems containing heterogeneous substructures are common in real-world applications. Various physical phenomena of the complex chemical systems are derived from the interactions between the heterogeneous substructures. However, existing graph representation learning methods for inter-graph interactions assumed graph-level interactions between homogeneous structures, such as organic molecules and inorganic crystalline materials. We propose a data descriptor of the complex chemical systems and a graph neural network for learning inter-graph interactions between organic and inorganic compounds. We applied the proposed method to predict the physical properties of hybrid solar cell materials containing heterogeneous substructures, which have received significant attention for sustainable energy resources. By learning heterogeneous inter-graph interactions, the proposed method achieved state-of-the-art accuracy in predicting band gaps of 1,682 hybrid solar cell materials.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.27614 [cs.LG] |
| (or arXiv:2610.27614v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.27614 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Gyoung S. Na [view email]
[v1]
Tue, 20 Oct 2026 04:27:45 UTC (226 KB)
来源：arXiv cs.AI · arxiv.org