We present a novel edge-level ego-network encoding for learning on graphs
that can boost Message Passing Graph Neural Networks (MP-GNNs) by providing
additional node and edge features or extending message-passing formats. The
proposed encoding is sufficient to distinguish Strongly Regular Graphs, a
family of challenging 3-WL equivalent graphs. We show theoretically that such
encoding is more expressive than node-based sub-graph MP-GNNs. In an empirical
evaluation on four benchmarks with 10 graph datasets, our results match or
improve previous baselines on expressivity, graph classification, graph
regression, and proximity tasks -- while reducing memory usage by 18.1x in
certain real-world settings.

通过提供额外的节点和边缘特征或扩展消息传递格式，我们提出了一种新颖的用于在图上学习的边缘级自我网络编码，可以提升消息传递图神经网络（MP-GNNs）的能力。理论上，该编码比基于节点的子图 MP-GNNs 更具表现力。在四个基准测试和 10 个图形数据集的实证评估中，我们的结果在表现力、图形分类、图形回归和接近性任务方面与之前的基准线相匹配或有所提高，同时在某些实际环境中减少了 18.1 倍的内存使用。