arXiv cs.AI· Sihan Liaing, Ji Zhang, Kehan Wang, Zihao Gao, Wei Ma, Yangang Wang, Zongguo Wang·· 10 小时前AI 评分22
基于置信度与图结构学习的材料数据质量评估框架
Confidence-Based Materials Data Quality Assessment via Domain Knowledge and Graph-Structured Learning
AI 导读
研究提出一种基于置信度的材料数据质量评估框架,将数据质量建模为连续置信度估计而非二元异常检测,结合九维特征质量先验、样本-特征二部图传播与弱监督图注意力,并用 Memory-GAT 模块做历史参考评分。
正文 · 原文
Abstract:The rapid development of materials machine learning relies on large-scale, heterogeneous datasets, yet model reliability is often compromised by imperfect data from diverse experiments, simulations, and database integration. Real-world materials databases may contain measurement errors, failed calculations, missing or duplicate records, and hidden violations of physicochemical constraints. Such problems are difficult to identify because corrupted samples may remain statistically plausible rather than appearing as explicit outliers. In this paper, we propose a confidence-based materials data quality assessment framework that integrates domain knowledge with graph-structured learning. Data quality is formulated as a continuous confidence estimation problem rather than a binary anomaly identification task, enabling sample-level assessment and historical-reference-based batch comparison. A nine-dimensional feature-quality prior and duplicate-aware sample initialization are calibrated using materials domain rules and statistical evidence. Confidence is further refined through sample-feature bipartite graph propagation and weakly supervised graph attention, while a Memory-GAT module provides historical reference scoring. Experiments on 23 ODDS benchmark datasets show that the generic module achieves an average AUC-ROC of 0.866. In five repeated mixed-contamination experiments on mp\_20, rule calibration improves HistGradientBoostingRegressor test $R^2$ from $0.538\pm0.008$ to $0.616\pm0.014$. Graph refinement increases average precision from $0.943\pm0.004$ to 0.953\pm0.004$, while the rule-calibrated configuration has the highest mean test $R^2$ among the evaluated screening configurations. Five repeated MACE subset experiments further show an increase in $R^2$ from $0.590\pm0.053$ to $0.880\pm0.027$ after rule-based screening.
| Subjects: | Machine Learning (cs.LG); Materials Science (cond-mat.mtrl-sci); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.23342 [cs.LG] |
| (or arXiv:2611.23342v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2611.23342 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Zongguo Wang [view email]
[v1]
Tue, 17 Nov 2026 08:06:38 UTC (6,626 KB)
来源:arXiv cs.AI · arxiv.org