用无监督方法学习晶体原子表示，提升材料性质预测精度。
UNATE: UNsupervised ATomic Embedding for crystal structures property prediction
- 通过自编码器与对比学习联合训练，从无标签晶体结构中提取原子嵌入。
- 在仅有25%标注数据时，性能提升达10%，全量数据下提升2.7%。
- 适合标注数据稀缺的材料发现场景，尤其利于小样本预测。
准确预测晶体性质对加速材料发现至关重要，但常受限于标注数据稀少和高成本的理论计算。为此，我们提出UNATE（无监督原子嵌入）框架，利用未标注晶体结构中的结构信息。UNATE结合无监督去噪自编码器与自监督对比学习，学习鲁棒的原子表示，并作为下游性质预测的输入特征。实验表明，用UNATE预训练的节点嵌入替代原始原子序数，相比全数据基线提升2.7%。在标注数据有限的情况下，优势更为显著：当仅使用25%标注数据时，性能提升最高达10%。
原文摘要 · Abstract (English)
Accurately predicting crystal properties is critical for accelerating materials discovery, but it is often limited by scarce labeled data and costly theoretical calculations. To alleviate this, we propose UNATE (Unsupervised Atomic Embedding), a framework that leverages structural information extracted from unlabeled crystal structures. UNATE integrates an unsupervised denoising autoencoder with self-supervised contrastive learning to learn robust atomic representations, which are then used as input features for downstream property prediction. Experimental results show that replacing raw atomic numbers with UNATE-pretrained node embeddings yields a 2.7\% improvement over the full-data baseline. Notably, the benefits become more pronounced in scenarios with limited labeled data, reaching improvements of up to 10\% when only 25\% of the labeled data is used.
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。