Proceedings

Translating Latent Representations for Money Laundering Detection

Ramon Rico, Ioana Hulpus, Stan Leisink, Boyang Zhao, Yannis Velegrakis

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. AI4Tech: AI Enabling Technologies. Pages 6500-6508.

https://doi.org/10.24963/ijcai.2026/723

Keywords

  • Domain-specific AI4Tech: AI4Finance

Abstract

Anti-money laundering (AML) systems are important for safe economic trade and for the fight against financial crime. Recently, a number of AML algorithms based on graph neural networks (GNNs) and graph transformers (GTs) have been proposed. Compared to traditional machine learning solutions, these methods have been shown to achieve significantly better detection results. Yet, the state-of-the-art AML algorithms have a key limitation: they fail to jointly address money laundering classification and money laundering sub-network discovery, despite their strong theoretical connection. To bridge this gap, we propose a translation-based AML system (TAML) that is capable of jointly solving both problems within the same latent space. Our extensive experimental evaluation on multiple datasets demonstrates the superiority of TAML over the state-of-the-art in both tasks.

Ramon Rico, Ioana Hulpus, Stan Leisink, Boyang Zhao, and Yannis Velegrakis. 2026. Translating Latent Representations for Money Laundering Detection. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 6500–6508. https://doi.org/10.24963/ijcai.2026/723
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards