A per-step layer-wise embedding exchange in federated GNNs recovers centralized node representations for cross-client subgraph patterns under an extended-subgraph assumption.
Provably powerful graph neural networks for directed multigraphs
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
ExSTraQt uses quasi-temporal graph representations and supervised learning to detect suspicious transactions, achieving F1 score uplifts of up to 1% on real data and over 8% on synthetic datasets compared to prior AML models.
GARG-AML detects smurfing in anti-money laundering using second-order graph neighborhood densities combined with machine learning classifiers for scalable and interpretable results.
citing papers explorer
-
Federated Cross-Client Subgraph Pattern Detection
A per-step layer-wise embedding exchange in federated GNNs recovers centralized node representations for cross-client subgraph patterns under an extended-subgraph assumption.
-
Extracting Money Laundering Transactions from Quasi-Temporal Graph Representation
ExSTraQt uses quasi-temporal graph representations and supervised learning to detect suspicious transactions, achieving F1 score uplifts of up to 1% on real data and over 8% on synthetic datasets compared to prior AML models.
-
GARG-AML against Smurfing: A Scalable and Interpretable Graph-Based Framework for Anti-Money Laundering
GARG-AML detects smurfing in anti-money laundering using second-order graph neighborhood densities combined with machine learning classifiers for scalable and interpretable results.