新算法融合边特征提升图同构检测，让图神经网络更懂图的连接信息。
Edged Weisfeiler-Lehman Algorithm
- 扩展经典1-WL算法，引入边特征进行颜色精炼
- 在12个带边特征的数据集上优于主流基线模型
- 适合处理含丰富边属性的图数据任务
作为图学习中的经典方法，传播-聚合范式被众多图神经网络（GNNs）采用，其中节点表示通过递归聚合自身及其邻居节点的表示来更新。类似地，Weisfeiler-Lehman（1-WL）算法通过节点及其邻居的颜色表示进行颜色精炼以测试同构性。然而，1-WL未利用任何边特征（标签），在某些领域存在改进空间。为解决这一局限，我们提出一种新型的带边1-WL算法（E-WL），将原始1-WL扩展以融合边特征。基于E-WL算法，我们进一步引入了带边图同构网络（EGIN）模型，以更好地利用图数据中的边特征，克服了多数GNN模型不使用边特征的关键缺陷。我们在12个带有边特征的基准图数据集上评估了所提模型性能，并与一些先进基线模型进行了比较。实验结果表明，所提出的EGIN模型在图分类任务中总体表现出更优性能。
原文摘要 · Abstract (English)
As a classical approach on graph learning, the propagation-aggregation methodology is widely exploited by many of Graph Neural Networks (GNNs), wherein the representation of a node is updated by aggregating representations from itself and neighbor nodes recursively. Similar to the propagation-aggregation methodology, the Weisfeiler-Lehman (1-WL) algorithm tests isomorphism through color refinement according to color representations of a node and its neighbor nodes. However, 1-WL does not leverage any edge features (labels), presenting a potential improvement on exploiting edge features in some fields. To address this limitation, we proposed a novel Edged-WL algorithm (E-WL) which extends the original 1-WL algorithm to incorporate edge features. Building upon the E-WL algorithm, we also introduce an Edged Graph Isomorphism Network (EGIN) model for further exploiting edge features, which addresses one key drawback in many GNNs that do not utilize any edge features of graph data. We evaluated the performance of proposed models using 12 edge-featured benchmark graph datasets and compared them with some state-of-the-art baseline models. Experimental results indicate that our proposed EGIN models, in general, demonstrate superior performance in graph learning on graph classification tasks.
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。