Graph Neural Networks with Precomputed Node Features

Egressy, Béni; Wattenhofer, Roger

doi:10.48550/arxiv.2206.00637

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another line of work uses pre-calculated features to augment the GNN. These works explore adding subgraph counts (Bouritsas et al 2022;Barceló et al 2021), positional node embeddings (Egressy and Wattenhofer 2022;Dwivedi et al 2021), random IDs (Abboud et al 2020;Sato, Yamada, and Kashima 2021), and node IDs (Loukas 2019).…”

Section: Related Workmentioning

confidence: 99%

Provably Powerful Graph Neural Networks for Directed Multigraphs

Egressy,

Von Niederhäusern,

Blanuša

et al. 2024

AAAI

View full text Add to dashboard Cite

This paper analyses a set of simple adaptations that transform standard message-passing Graph Neural Networks (GNN) into provably powerful directed multigraph neural networks. The adaptations include multigraph port numbering, ego IDs, and reverse message passing. We prove that the combination of these theoretically enables the detection of any directed subgraph pattern. To validate the effectiveness of our proposed adaptations in practice, we conduct experiments on synthetic subgraph detection tasks, which demonstrate outstanding performance with almost perfect results. Moreover, we apply our proposed adaptations to two financial crime analysis tasks. We observe dramatic improvements in detecting money laundering transactions, improving the minority-class F1 score of a standard message-passing GNN by up to 30%, and closely matching or outperforming tree-based and GNN baselines. Similarly impressive results are observed on a real-world phishing detection dataset, boosting three standard GNNs’ F1 scores by around 15% and outperforming all baselines. An extended version with appendices can be found on arXiv: https://arxiv.org/abs/2306.11586.

show abstract