Improving Subgraph-GNNs via Edge-Level Ego-Network Encodings

Published: 02 May 2024, Last Modified: 02 May 2024Accepted by TMLREveryoneRevisionsBibTeX
Abstract: 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.
Submission Length: Long submission (more than 12 pages of main content)
Assigned Action Editor: ~Giannis_Nikolentzos1
Submission Number: 1844