用可解释的KAN网络预测晶体能量，发现与周期表一致的化学规律。
Interpretation of Crystal Energy Landscapes with Kolmogorov-Arnold Networks
- 用可学习函数替代固定激活函数，提升模型可解释性
- 在大尺度数据上准确预测形成能、带隙和功函数
- 无需物理约束即发现周期表规律，适合材料机理研究
刻画晶态能量景观对于预测热力学稳定性、电子结构和功能行为至关重要。尽管机器学习可快速预测性质，但多数模型的“黑箱”特性限制了其生成新科学洞见的能力。本文引入柯尔莫哥洛夫-阿诺德网络（KANs），作为可解释框架以弥合这一差距。与传统神经网络采用固定激活函数不同，KANs使用可学习函数揭示潜在物理关系。我们提出仅基于组分的元素加权KAN模型，在大规模数据集上实现了形成能、带隙和功函数预测的最先进精度。关键的是，无需显式物理约束，通过嵌入分析、相关性研究和主成分分析，KANs自动揭示了与周期表及量子力学原理一致的可解释化学趋势。结果表明，KANs兼具高预测性能与科学可解释性，为透明化、基于化学的材料信息学提供了新范式。
原文摘要 · Abstract (English)
Characterizing crystalline energy landscapes is essential to predicting thermodynamic stability, electronic structure, and functional behavior. While machine learning (ML) enables rapid property predictions, the "black-box" nature of most models limits their utility for generating new scientific insights. Here, we introduce Kolmogorov-Arnold Networks (KANs) as an interpretable framework to bridge this gap. Unlike conventional neural networks with fixed activation functions, KANs employ learnable functions that reveal underlying physical relationships. We developed the Element-Weighted KAN, a composition-only model that achieves state-of-the-art accuracy in predicting formation energy, band gap, and work function across large-scale datasets. Crucially, without any explicit physical constraints, KANs uncover interpretable chemical trends aligned with the periodic table and quantum mechanical principles through embedding analysis, correlation studies, and principal component analysis. These results demonstrate that KANs provide a powerful framework with high predictive performance and scientific interpretability, establishing a new paradigm for transparent, chemistry-based materials informatics.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。