mlsanityData to 14 Oct 2026

Provably Powerful Graph Neural Networks for Directed Multigraphs

arXiv 2306.11586 ↗First posted 20 Jun 2023cs.LG cs.AIcited by 27

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 27 papers in the map (data through 14 Oct 2026). Builds on 53 of its 79 references that are in the map. First posted on arXiv 20 Jun 2023.

Builds on

53 of 79 references.

References · 53

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2017Graph Attention Networkscited by 8,923
  3. 2017Inductive Representation Learning on Large Graphscited by 6,320
  4. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
  5. 2018How Powerful are Graph Neural Networks?cited by 4,393
  6. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
  7. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
  8. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,694
  9. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,576
  10. 2018Relational inductive biases, deep learning, and graph networkscited by 1,360
  11. 2018Deep Graph Infomaxcited by 1,106
  12. 2019Strategies for Pre-training Graph Neural Networkscited by 971
38 more
  1. 2018Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networkscited by 881
  2. 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 826
  3. 2016Interaction Networks for Learning about Objects, Relations and Physicscited by 509
  4. 2019Provably Powerful Graph Networkscited by 389
  5. 2021Graph Neural Networks with Learnable Structural and Positional Representationscited by 333
  6. 2020Improving Graph Neural Network Expressivity via Subgraph Isomorphism Countingcited by 313
  7. 2021Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methodscited by 311
  8. 2020Can Graph Neural Networks Count Substructures?cited by 236
  9. 2020Generalization and Representational Limits of Graph Neural Networkscited by 218
  10. 2019What graph neural networks cannot learn: depth vs widthcited by 201
  11. 2020The Surprising Power of Graph Neural Networks with Random Node Initializationcited by 198
  12. 2021Identity-aware Graph Neural Networkscited by 198
  13. 2020Random Features Strengthen Graph Neural Networkscited by 186
  14. 2019On the equivalence between graph isomorphism testing and function approximation with GNNscited by 172
  15. 2022Forecasting Global Weather with Graph Neural Networkscited by 168
  16. 2019Anti-Money Laundering in Bitcoin: Experimenting with Graph Convolutional Networks for Financial Forensicscited by 164
  17. 2021From Stars to Subgraphs: Uplifting Any GNN with Local Structure Awarenesscited by 155
  18. 2021Nested Graph Neural Networkscited by 137
  19. 2021ETA Prediction with Graph Neural Networks in Google Mapscited by 130
  20. 2021DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networkscited by 118
  21. 2022Understanding and Extending Subgraph GNNs by Rethinking Their Symmetriescited by 112
  22. 2021MagNet: A Neural Network for Directed Graphscited by 107
  23. 2018Temporal Relational Ranking for Stock Predictioncited by 102
  24. 2020Heterogeneous Graph Neural Networks for Malicious Account Detectioncited by 96
  25. 2017Beyond News Contents: The Role of Social Context for Fake News Detectioncited by 91
  26. 2020Molecular graph generation with Graph Neural Networkscited by 80
  27. 2019Approximation Ratios of Graph Neural Networks for Combinatorial Problemscited by 69
  28. 2022Boosting the Cycle Counting Power of Graph Neural Networks with I2-GNNscited by 56
  29. 2021Graph Neural Networks with Local Graph Parameterscited by 52
  30. 2022Gradient Gating for Deep Multi-Rate Learning on Graphscited by 49
  31. 2022A Theoretical Comparison of Graph Neural Network Extensionscited by 48
  32. 2019Spectral-based Graph Convolutional Network for Directed Graphscited by 38
  33. 2018Scalable Graph Learning for Anti-Money Laundering: A First Lookcited by 33
  34. 2020xFraud: Explainable Fraud Transaction Detectioncited by 28
  35. 2022LaundroGraph: Self-Supervised Graph Representation Learning for Anti-Money Launderingcited by 20
  36. 2019edGNN: a Simple and Powerful GNN for Directed Labeled Graphscited by 18
  37. 2020Uncovering Insurance Fraud Conspiracy with Network Learningcited by 9
  38. 2022Ethereum Fraud Detection with Heterogeneous Graph Neural Networkscited by 9

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 5; 2025: 9; 2026: 12.

27 papers.

Sort:

  1. 2023Realistic Synthetic Financial Transactions for Anti-Money Laundering Modelscited by 50
  2. 2024Network Analytics for Anti-Money Laundering -- A Systematic Literature Review and Experimental Evaluationcited by 7
  3. 2026Learning Graph Foundation Models on Riemannian Graph-of-Graphscited by 3
  4. 2024Towards Data-centric Machine Learning on Directed Graphs: a Surveycited by 2
  5. 2025TeMP-TraG: Edge-based Temporal Message Passing in Transaction Graphscited by 2
  6. 2024Privacy-Preserving Graph-Based Machine Learning with Fully Homomorphic Encryption for Collaborative Anti-Money Launderingcited by 1
  7. 2024MEGA: Message Passing Neural Networks for Multigraphs with EdGe Attributescited by 1
  8. 2025Graph machine learning for flight delay prediction due to holding manouvercited by 1
  9. 2025Towards Collaborative Anti-Money Laundering Among Financial Institutionscited by 1
  10. 2025Deep Learning Approaches for Anti-Money Laundering on Mobile Transactions: Review, Framework, and Directionscited by 1
  11. 2025Advances in Continual Graph Learning for Anti-Money Laundering Systems: A Comprehensive Reviewcited by 1
  12. 2025ATM-GAD: Adaptive Temporal Motif Graph Anomaly Detection for Financial Transaction Networkscited by 1
15 more
  1. 2024Multi-Class and Multi-Task Strategies for Neural Directed Link Predictioncited by 0
  2. 2025GARG-AML against Smurfing: A Scalable and Interpretable Graph-Based Framework for Anti-Money Launderingcited by 0
  3. 2025HSG-12M: A Large-Scale Benchmark of Spatial Multigraphs from the Energy Spectra of Non-Hermitian Crystalscited by 0
  4. 2025FD4QC: Application of Classical and Quantum-Hybrid Machine Learning for Financial Fraud Detection A Technical Reportcited by 0
  5. 2026A Tight Expressivity Hierarchy for GNN-Based Entity Resolution in Master Data Managementcited by 0
  6. 2026Extracting Money Laundering Transactions from Quasi-Temporal Graph Representationcited by 0
  7. 2026TransXion: A High-Fidelity Graph Benchmark for Realistic Anti-Money Launderingcited by 0
  8. 2026Federated Layer-Wise Exchange for Cross-Client Money Laundering Pattern Detectioncited by 0
  9. 2026Provably Communication-Efficient and Privacy-Preserving Federated Graph Neural Networkscited by 0
  10. 2026Choosing a parallel heterogeneous ensemble method for tabular classificationcited by 0
  11. 2026SALT-GNN: Handling Dense Neighborhoods in Anti-Money Laundering Graphs via Statistics-Aware Attentioncited by 0
  12. 2026Population-Calibrated Graph Screening at 835-Million-Address Scale, with Label-Free Transfer to New Chainscited by 0
  13. 2026Dual-Scale Relational Graph Transformers for Ecosystem-Aware Fraud Detectioncited by 0
  14. 2026Privacy-Preserving GNN Inference on Financial Transaction Graphs via Homomorphic Encryptioncited by 0
  15. 2026Random Probing for Structural Self-Interactions in Graph Neural Networkscited by 0