GRANDE: a neural model over directed multigraphs with application to anti-money laundering

TL;DR

GRANDE is a novel neural network architecture designed for directed multigraphs, effectively capturing directional and edge-specific information, and demonstrating superior performance in anti-money laundering and dynamic graph tasks.

Contribution

The paper introduces GRANDE, a new GNN protocol and architecture tailored for directed multigraphs and edge classification, addressing limitations of existing models in financial risk management.

Findings

GRANDE outperforms state-of-the-art models on real-world AML tasks.

The model effectively captures directional information in directed multigraphs.

Experimental results validate GRANDE's superiority in dynamic and directed graph modeling.

Abstract

The application of graph representation learning techniques to the area of financial risk management (FRM) has attracted significant attention recently. However, directly modeling transaction networks using graph neural models remains challenging: Firstly, transaction networks are directed multigraphs by nature, which could not be properly handled with most of the current off-the-shelf graph neural networks (GNN). Secondly, a crucial problem in FRM scenarios like anti-money laundering (AML) is to identify risky transactions and is most naturally cast into an edge classification problem with rich edge-level features, which are not fully exploited by the prevailing GNN design that follows node-centric message passing protocols. In this paper, we present a systematic investigation of design aspects of neural models over directed multigraphs and develop a novel GNN protocol that overcomes the above challenges via efficiently incorporating directional information, as well as proposing an enhancement that targets edge-related tasks using a novel message passing scheme over an extension of edge-to-node dual graph. A concrete GNN architecture called GRANDE is derived using the proposed protocol, with several further improvements and generalizations to temporal dynamic graphs. We apply the GRANDE model to both a real-world anti-money laundering task and public datasets. Experimental evaluations show the superiority of the proposed GRANDE architecture over recent state-of-the-art models on dynamic graph modeling and directed graph modeling.