用超图网络更精准建模多反应物化学反应，提升虚拟筛选效率。
ChemHGNN: A Hierarchical Hypergraph Neural Network for Reaction Virtual Screening and Discovery
- 通过超边天然建模多反应物关系，避免传统图网络的复杂构建。
- 在USPTO数据集上显著优于GNN和HGNN基线，大样本下优势更明显。
- 结合反应中心感知采样与分层特征，兼顾准确率与化学合理性。
反应虚拟筛选与发现是化学与材料科学中的核心挑战，传统图神经网络（GNN）难以有效建模多反应物相互作用。本文提出ChemHGNN，一种用于反应网络的层次化超图神经网络（HGNN）框架，能有效捕捉反应中的高阶关系。与需为多反应物反应构建完整图的GNN不同，ChemHGNN通过超边自然建模多反应物反应，实现更具表达力的反应表征。针对组合爆炸、模型坍缩及化学无效负样本等关键问题，我们引入反应中心感知负采样策略（RCNS）和融合分子、反应及超图层级特征的分层嵌入方法。在USPTO数据集上的实验表明，ChemHGNN显著优于HGNN与GNN基线，尤其在大规模场景中表现突出，同时保持可解释性与化学合理性。本工作确立了超图网络在反应虚拟筛选与发现中的优越性，提供了一种化学信息驱动的加速反应发现框架。
原文摘要 · Abstract (English)
Reaction virtual screening and discovery are fundamental challenges in chemistry and materials science, where traditional graph neural networks (GNNs) struggle to model multi-reactant interactions. In this work, we propose ChemHGNN, a hypergraph neural network (HGNN) framework that effectively captures high-order relationships in reaction networks. Unlike GNNs, which require constructing complete graphs for multi-reactant reactions, ChemHGNN naturally models multi-reactant reactions through hyperedges, enabling more expressive reaction representations. To address key challenges, such as combinatorial explosion, model collapse, and chemically invalid negative samples, we introduce a reaction center-aware negative sampling strategy (RCNS) and a hierarchical embedding approach combining molecule, reaction and hypergraph level features. Experiments on the USPTO dataset demonstrate that ChemHGNN significantly outperforms HGNN and GNN baselines, particularly in large-scale settings, while maintaining interpretability and chemical plausibility. Our work establishes HGNNs as a superior alternative to GNNs for reaction virtual screening and discovery, offering a chemically informed framework for accelerating reaction discovery.
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。