edGNN: a Simple and Powerful GNN for Directed Labeled Graphs

The ability of a graph neural network (GNN) to leverage both the graph topology and graph labels is fundamental to building discriminative node and graph embeddings. Building on previous work, we theoretically show that edGNN, our model for directed labeled graphs, is as powerful as the Weisfeiler-Lehman algorithm for graph isomorphism. Our experiments support our theoretical findings, confirming that graph neural networks can be used effectively for inference problems on directed graphs with both node and edge labels. Code available at https://github.com/guillaumejaume/edGNN.

PDF Abstract


Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Graph Classification MUTAG edGNN (max) Accuracy 88.8% # 32
Graph Classification MUTAG edGNN (avg) Accuracy 86.9% # 48