Provably Powerful Graph Neural Networks for Directed Multigraphs
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2023
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911747851419648 |
|---|---|
| author | Egressy, Béni von Niederhäusern, Luc Blanusa, Jovan Altman, Erik Wattenhofer, Roger Atasu, Kubilay |
| author_facet | Egressy, Béni von Niederhäusern, Luc Blanusa, Jovan Altman, Erik Wattenhofer, Roger Atasu, Kubilay |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2306_11586 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Provably Powerful Graph Neural Networks for Directed Multigraphs Egressy, Béni von Niederhäusern, Luc Blanusa, Jovan Altman, Erik Wattenhofer, Roger Atasu, Kubilay Machine Learning Artificial Intelligence 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. |
| title | Provably Powerful Graph Neural Networks for Directed Multigraphs |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2306.11586 |