系统梳理图匹配神经模型的设计空间，发现新组合能显著提升性能。
Charting the Design Space of Neural Graph Representations for Subgraph Matching
- 将图匹配方法统一为包含注意力与软置换等轴的设计空间。
- 发现未探索的组合配置可使匹配准确率显著提升。
- 适合图神经网络、知识图谱和分子设计领域的研究者参考。
子图匹配在知识图谱问答、分子设计、场景图、代码与电路搜索等领域至关重要。近年来的神经方法展现了良好效果。我们对现有系统的研究表明，可将其重构为统一的图匹配网络设计空间。然而，现有方法仅占据该空间中少数孤立区域，整体仍待探索。本文首次全面探索这一设计空间，涵盖查询图与语料图间交互方式（如基于注意力或软置换）、节点对齐与边对齐，以及最终评分网络的形式等关键维度。大量实验表明，精心选择且此前未被探索的组合能带来显著性能提升。除性能改进外，本研究还揭示了有价值的设计洞见，建立了通用的神经图表示与交互原则，具有更广泛的研究意义。
原文摘要 · Abstract (English)
Subgraph matching is vital in knowledge graph (KG) question answering, molecule design, scene graph, code and circuit search, etc. Neural methods have shown promising results for subgraph matching. Our study of recent systems suggests refactoring them into a unified design space for graph matching networks. Existing methods occupy only a few isolated patches in this space, which remains largely uncharted. We undertake the first comprehensive exploration of this space, featuring such axes as attention-based vs. soft permutation-based interaction between query and corpus graphs, aligning nodes vs. edges, and the form of the final scoring network that integrates neural representations of the graphs. Our extensive experiments reveal that judicious and hitherto-unexplored combinations of choices in this space lead to large performance benefits. Beyond better performance, our study uncovers valuable insights and establishes general design principles for neural graph representation and interaction, which may be of wider interest.
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。