构建实验条件下的能带预测基准，提升模型可靠性。
Benchmarking bandgap prediction in semiconductors under experimental and realistic evaluation settings
- 基于实验测量数据构建新基准，匹配晶体结构。
- 模型在真实场景下泛化能力差，尤其跨计算与实验域时。
- 适合材料发现与机器学习可解释性研究者参考。
准确预测半导体能带隙对材料应用至关重要，但现有基于计算数据训练的机器学习模型在面对实验测量值时往往泛化能力不足。数据真实性、领域泛化与模型可解释性在现有评估框架中仍未充分解决。为此，我们提出 RealMat-BaG 基准，用于评估模型在实验相关条件下的可靠性。我们整理了一个开源的实验能带隙数据集，包含对齐的晶体结构，并比较了图神经网络与经典机器学习基线。评估涵盖统计与领域划分、从DFT计算值到实验值的迁移性能，以及元素属性与结构层面的可解释性分析。结果揭示了当前能带预测模型的根本性泛化局限，并建立了一个与实验测量对齐的基准，为开发更可靠的材料发现学习策略提供支持。
原文摘要 · Abstract (English)
Accurate bandgap prediction is crucial for semiconductor applications, yet machine learning models trained on computational data often struggle to generalize to experimental bandgap measurements. Challenges related to data fidelity, domain generalization, and model interpretability remain insufficiently addressed in existing evaluation frameworks. To bridge this gap, we introduce RealMat-BaG, a benchmark for assessing model reliability under experimentally relevant conditions. We curate an open-access dataset of experimental bandgaps with aligned crystal structures and compare graph neural networks as well as classical machine learning baselines. Our framework evaluates performance across statistical and domain-based splits, examines transfer from DFT-computed to experimental bandgaps, and analyzes interpretability at both elemental-property and structural levels. Our results reveal the fundamental generalization limitations of current bandgap prediction models and establish a benchmark aligned with experimental measurements for developing more reliable learning strategies for materials discovery.
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。