从稀缺标签和未标记晶体中学习材料属性
Learning Materials Properties from Scarce Labels and Unlabeled Crystals
查看机构详情
- Tsinghua University（清华大学）
- State Key Laboratory of Chemical Engineering and Low-Carbon Technology（化学工程与低碳技术国家重点实验室）
- Beijing Key Laboratory of Artificial Intelligence for Advanced Chemical Engineering Materials（先进化工材料人工智能北京市重点实验室）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
该研究针对稀缺标签和未标记晶体的材料属性学习挑战，提出半监督材料属性回归基准SemiMat与可靠性加权目标MatRank，经实验验证MatRank可降低测试误差并提升方法排名。
中文摘要 AI 辅助
从稀缺标签和未标记晶体中学习材料属性是数据驱动材料发现的核心挑战。我们提出了SemiMat，这是一个用于半监督材料属性回归的受控基准；以及MatRank，这是一个用于连续伪标签不确定性的可靠性加权目标。SemiMat固定了标记和未标记晶体输入、图骨干接口、仅验证的检查点选择、保留的测试报告、归一化平均绝对误差（NMAE），以及在6个稀缺标签任务、4个图骨干和5个预定义拆分运行中的方法排名汇总。MatRank从标记锚点构建伪目标，通过局部可靠性和弱预测一致性对其进行加权，一致地训练弱和强图视图，并添加排名信号，使未标记晶体同时影响值和候选顺序。在保留的24个骨干-任务模块中，一个固定的MatRank目标实现了最低的汇总保留测试NMAE（0.896）和最佳平均方法排名（2.208）。分布外（OOD）、组件和生成池诊断确定了收益可靠的位置以及仍需进一步筛选评估的位置。代码可在指定的URL获取。
英文摘要
Learning materials properties from scarce labels and unlabeled crystals is a central challenge for data-driven materials discovery. We present SemiMat, a controlled benchmark for semi-supervised materials property regression, and MatRank, a reliability-weighted objective for continuous pseudo-label uncertainty. SemiMat fixes labeled and unlabeled crystal inputs, graph-backbone interfaces, validation-only checkpoint selection, held-out test reporting, normalized MAE (NMAE), and method-rank summaries across six scarce-label tasks, four graph backbones, and five predefined split runs. MatRank builds pseudo-targets from labeled anchors, weights them by local reliability and weak-prediction agreement, trains weak and strong graph views consistently, and adds ranking signals so that unlabeled crystals shape both values and candidate order. Across the retained 24 backbone-task blocks, one fixed MatRank objective gives the lowest aggregate held-out test NMAE (0.896) and best average method rank (2.208). The component, OOD, and generated-pool diagnostics identify where the gain is reliable and where further screening evaluation remains necessary. Code is available at https://github.com/littlepeachs/SemiMat.
