Advances in Continual Graph Learning for Anti-Money Laundering Systems: A Comprehensive Review

Abstract

Financial institutions are required by regulation to report suspicious financial transactions related to money laundering. Therefore, they need to constantly monitor vast amounts of incoming and outgoing transactions. A particular challenge in detecting money laundering is that money launderers continuously adapt their tactics to evade detection. Hence, detection methods need constant fine-tuning. Traditional machine learning models suffer from catastrophic forgetting when fine-tuning the model on new data, thereby limiting their effectiveness in dynamic environments. Continual learning methods may address this issue and enhance current anti-money laundering (AML) practices, by allowing models to incorporate new information while retaining prior knowledge. Research on continual graph learning for AML, however, is still scarce. In this review, we critically evaluate state-of-the-art continual graph learning approaches for AML applications. We categorise methods into replay-based, regularization-based, and architecture-based strategies within the graph neural network (GNN) framework, and we provide in-depth experimental evaluations on both synthetic and real-world AML data sets that showcase the effect of the different hyperparameters. Our analysis demonstrates that continual learning improves model adaptability and robustness in the face of extreme class imbalances and evolving fraud patterns. Finally, we outline key challenges and propose directions for future research.

References in corpus (21)

• Semi-Supervised Classification with Graph Convolutional Networks
• Overcoming catastrophic forgetting in neural networks
• A continual learning survey: Defying forgetting in classification tasks
• An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks
• How Powerful are Graph Neural Networks?
• Class-Incremental Learning: A Survey
• Alleviating catastrophic forgetting using context-dependent gating and synaptic stabilization
• Using social network analysis to prevent money laundering
• Anti-Money Laundering in Bitcoin: Experimenting with Graph Convolutional Networks for Financial Forensics
• Toward Understanding Catastrophic Forgetting in Continual Learning
• Architecture Matters in Continual Learning
• Lifelong Learning on Evolving Graphs Under the Constraints of Imbalanced Classes and New Classes
• Structure-free Graph Condensation: From Large-scale Graphs to Condensed Graph-free Data
• Topology-Agnostic Detection of Temporal Money Laundering Flows in Billion-Scale Transactions
• Continual Learning on Graphs: Challenges, Solutions, and Opportunities
• Continual Learning for Unsupervised Anomaly Detection in Continuous Auditing of Financial Accounting Data
• Benchmarking Sensitivity of Continual Graph Learning for Skeleton-Based Action Recognition
• BeGin: Extensive Benchmark Scenarios and An Easy-to-use Framework for Graph Continual Learning
• Hyperparameters in Continual Learning: A Reality Check
• AGALE: A Graph-Aware Continual Learning Evaluation Framework
• Forgetting Prevention for Cross-regional Fraud Detection with Heterogeneous Trade Graph