加速材料发现：学习化学过程的通用表示以实现跨领域性质预测
Accelerating Materials Discovery: Learning a Universal Representation of Chemical Processes for Cross-Domain Property Prediction
AI总结：
本文提出了一种通用的过程图表示，通过多模态图神经网络实现跨领域性质预测，展示了大规模学习的通用表示在专门任务中的高效迁移能力。
摘要：
化学过程的实验验证是缓慢且昂贵的，限制了材料发现的探索。机器学习可以优先考虑有前途的候选者，但现有专利和文献中的数据是异构的，难以利用。我们引入了一种通用的有向树过程图表示，将非结构化文本、分子结构和数值测量统一到单一的可机读格式中。为了从这种结构化数据中学习，我们开发了多模态图神经网络，具有属性条件注意力机制。在近9000份不同文档中提取的约70万过程图上训练，我们的模型学习了语义丰富的嵌入，能够在不同领域间泛化。当在紧凑的、领域特定的数据集上微调时，预训练模型表现出色，证明了在大规模学习过程中获得的通用过程表示能够有效转移到专门的预测任务中，仅需少量额外数据。
英文摘要：
Experimental validation of chemical processes is slow and costly, limiting exploration in materials discovery. Machine learning can prioritize promising candidates, but existing data in patents and literature is heterogeneous and difficult to use. We introduce a universal directed-tree process-graph representation that unifies unstructured text, molecular structures, and numeric measurements into a single machine-readable format. To learn from this structured data, we developed a multi-modal graph neural network with a property-conditioned attention mechanism. Trained on approximately 700,000 process graphs from nearly 9,000 diverse documents, our model learns semantically rich embeddings that generalize across domains. When fine-tuned on compact, domain-specific datasets, the pretrained model achieves strong performance, demonstrating that universal process representations learned at scale transfer effectively to specialized prediction tasks with minimal additional data.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
