Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Edged Weisfeiler-Lehman Algorithm

About

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.

Xiao Yue, Bo Liu, Feng Zhang, Guangzhi Qu• 2025

Related benchmarks

TaskDatasetResultRank
Graph ClassificationMUTAG
Accuracy92.8
697
Graph ClassificationPTC-MR
Accuracy62.2
153
Graph ClassificationPTC FM
Accuracy63.4
59
Graph ClassificationAIDS
Accuracy99.7
48
Graph ClassificationPTC FR
Accuracy68.9
26
Graph ClassificationPTC MM
Accuracy65.6
26
Graph ClassificationCOX2-MD
Accuracy74.2
25
Graph ClassificationTox21 AhR
Accuracy89.4
20
Graph ClassificationCUNEIFORM
Accuracy91.7
15
Graph ClassificationTox21 AR
Accuracy0.981
10
Showing 10 of 11 rows

Other info

Follow for update