用新架构让图神经网络更深更强，加速材料性能预测
DenseGNN: universal and scalable deeper graph neural networks for high-performance property prediction in crystals and molecules
- 引入密集连接与层级残差结构，突破深层GNN训练难题
- 在多个数据集上超越现有模型，晶体结构区分接近实验精度
- 适合需要高效精准材料性质预测的研究者使用
生成模型产生了大量假设材料，亟需快速准确的性质预测工具。图神经网络（GNN）在此领域表现优异，但面临训练成本高、领域适应难和过平滑等问题。我们提出DenseGNN，结合密集连接网络（DCN）、层级节点-边-图残差网络（HRN）和局部结构序参数嵌入（LOPE），有效解决上述挑战。DenseGNN在JARVIS-DFT、Materials Project和QM9等数据集上达到领先性能，显著提升GIN、Schnet和Hamnet等模型在材料数据上的表现。通过优化原子嵌入并降低计算开销，DenseGNN支持更深网络结构，在晶体结构区分能力上超越其他GNN，接近X射线衍射方法精度，推动材料发现与设计进程。
原文摘要 · Abstract (English)
Generative models generate vast numbers of hypothetical materials, necessitating fast, accurate models for property prediction. Graph Neural Networks (GNNs) excel in this domain but face challenges like high training costs, domain adaptation issues, and over-smoothing. We introduce DenseGNN, which employs Dense Connectivity Network (DCN), Hierarchical Node-Edge-Graph Residual Networks (HRN), and Local Structure Order Parameters Embedding (LOPE) to address these challenges. DenseGNN achieves state-of-the-art performance on datasets such as JARVIS-DFT, Materials Project, and QM9, improving the performance of models like GIN, Schnet, and Hamnet on materials datasets. By optimizing atomic embeddings and reducing computational costs, DenseGNN enables deeper architectures and surpasses other GNNs in crystal structure distinction, approaching X-ray diffraction method accuracy. This advances materials discovery and design.
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。