References & Citations
Computer Science > Machine Learning
Title: Improving Subgraph-GNNs via Edge-Level Ego-Network Encodings
(Submitted on 10 Dec 2023 (v1), last revised 2 May 2024 (this version, v2))
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 history
From: Francisco Nurudin Alvarez Gonzalez [view email][v1] Sun, 10 Dec 2023 15:05:23 GMT (618kb,D)
[v2] Thu, 2 May 2024 12:18:43 GMT (654kb,D)
Link back to: arXiv, form interface, contact.