Graph-Driven Framework for Anti-Money Laundering in Mobility-Energy Supply Chains
A research article introduces a real-time anti-money laundering monitoring framework (GCRMF) driven by graphs, aimed at integrated travel-energy supply chain networks. This framework develops a cross-industry heterogeneous graph (CIHG) that includes new energy vehicle rental services, energy providers, and fintech organizations. It employs a Temporal Dual-Graph Attention Network (Temporal Dual-GAT) to dynamically capture the evolution of capital flow paths over time. Additionally, to detect collusive structural fraud, a meta-path subgraph reasoning module that utilizes contrastive learning and hierarchical graph sampling is proposed. The paper can be found on arXiv with the identifier 2605.18844.
Key facts
- arXiv paper 2605.18844 proposes GCRMF framework
- Framework targets anti-money laundering in travel-energy supply chains
- Uses cross-industry heterogeneous graph (CIHG)
- Employs Temporal Dual-Graph Attention Network (Temporal Dual-GAT)
- Includes meta-path subgraph reasoning module
- Module uses contrastive learning and hierarchical graph sampling
- Covers new energy vehicle rental platforms, energy suppliers, fintech institutions
- Focuses on real-time monitoring and structural fraud detection
Entities
Institutions
- arXiv