LineMVGNN: Anti-Money Laundering with Line-Graph-Assisted Multi-View Graph Neural Networks

Paper: arXiv 2603.23584

Authors: Chung-Hoo Poon, James Kwok, Calvin Chow, Jang-Hyeon Choi

Abstract

Anti-money laundering (AML) systems are important for protecting the global economy. However, conventional rule-based methods rely on domain knowledge, leading to suboptimal accuracy and a lack of scalability. Graph neural networks (GNNs) for digraphs (directed graphs) can be applied to transaction graphs and capture suspicious transactions or accounts. However, most spectral GNNs do not naturally support multi-dimensional edge features, lack interpretability due to edge modifications, and have limited scalability owing to their spectral nature. Conversely, most spatial methods may not capture the money flow well. Therefore, in this work, we propose LineMVGNN (Line-Graph-Assisted Multi-View Graph Neural Network), a novel spatial method that considers payment and receipt transactions. Specifically, the LineMVGNN model extends a lightweight MVGNN module, which performs two-way message passing between nodes in a transaction graph. Additionally, LineMVGNN incorporates a line graph view of the original transaction graph to enhance the propagation of transaction information. We conduct experiments on two real-world account-based transaction datasets: the Ethereum phishing transaction network dataset and a financial payment transaction dataset from one of our industry partners. The results show that our proposed method outperforms state-of-the-art methods, reflecting the effectiveness of money laundering detection with line-graph-assisted multi-view graph learning. We also discuss scalability, adversarial robustness, and regulatory considerations of our proposed method.

Complexity vs Empirical Score

• Math Complexity: 6.5/10
• Empirical Rigor: 8.0/10
• Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: The paper introduces a novel spatial GNN architecture (LineMVGNN) tailored for directed transaction graphs by using dual message passing and a line graph view. The empirical evaluation is strong, leveraging both real-world Ethereum network data and proprietary financial payment data to demonstrate superior detection accuracy over existing SOTA methods.

Research Flowchart

  flowchart TD
    A[Goal: Enhance AML Detection with Scalable & Interpretable GNNs] --> B[Input Data: Ethereum Phishing & Industry Payment Datasets]
    B --> C[LineMVGNN Framework Construction]
    C --> D[Multi-View Graph Learning: Two-Way Message Passing]
    C --> E[Line Graph View: Enhanced Transaction Propagation]
    D & E --> F[Outcomes: Outperforms SOTA Methods in AML Detection]
    F --> G[Validated Robustness, Scalability & Regulatory Compliance]

Cited References (74)

1. Who Are the Phishers? Phishing Scam Detection on Ethereum via Network Embedding (2022)
2. Ethereum fraud detection with heterogeneous graph neural networks (2022) — link
3. Phishing Scams Detection in Ethereum Transaction Network (2020)
4. Semi-Supervised Classification with Graph Convolutional Networks (2017)
5. Simplifying Graph Convolutional Networks (2019)
6. Inductive Representation Learning on Large Graphs. (2017)
7. Strategies for Pre-training Graph Neural Networks. (2020)
8. Neural message passing for Quantum chemistry (2017)

0 of 74 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.