Back to feed
arXiv cs.LG
arXiv cs.LG
6/26/2026
Clue-Guided Money Laundering Group Discovery

Clue-Guided Money Laundering Group Discovery

Short summary

Researchers introduce Clue2Group, a graph neural network framework for identifying money laundering networks from investigative clues. Using local-temporal GNNs and multi-semantic evidence, it progressively maps criminal structures while preserving laundering patterns. Tested on two AML benchmarks, it bridges academic anomaly detection with real investigation workflows.

  • •Novel GNN framework starts from investigative clues rather than whole-network searches
  • •Uses local-temporal graph neural networks to preserve chain and cycle laundering patterns
  • •Designed to match real AML analyst workflows, not just produce risk alerts

Generated with AI, which can make mistakes.

#research-breakthrough#ai-tools#ai-agents#regulation-policy
Read full article at arXiv cs.LG

Is this a good recommendation for you?

Explore more

CIExplainer++: Generating Causal and Interpretable Explanations for Graph Neural Networks
arXiv cs.LG
Detecting Hallucinations for Large Language Model-based Knowledge Graph Reasoning
arXiv cs.CL
Federated Hash Projected Latent Factor Learning
arXiv cs.LG
Hierarchical Multi-Scale Graph Neural Networks: Scalable Heterophilous Learning with Oversmoothing and Oversquashing Mitigation
arXiv cs.LG