RMGANets: reinforcement learning-enhanced multi-relational attention graph-aware network for anti-money laundering detection
Abstract Given the anonymity and complexity of illegal transactions, traditional deep-learning methods struggle to establish correlations between transaction addresses, cash flows, and physical users. Additionally, the limited number of labels for illegal transactions results in severe class imbalan...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2024-11-01
|
| Series: | Complex & Intelligent Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s40747-024-01615-9 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832571206628278272 |
|---|---|
| author | Qianyu Wang Wei-Tek Tsai Bowen Du |
| author_facet | Qianyu Wang Wei-Tek Tsai Bowen Du |
| author_sort | Qianyu Wang |
| collection | DOAJ |
| description | Abstract Given the anonymity and complexity of illegal transactions, traditional deep-learning methods struggle to establish correlations between transaction addresses, cash flows, and physical users. Additionally, the limited number of labels for illegal transactions results in severe class imbalance and other challenges. To overcome these limitations, we propose a reinforcement learning-enhanced, multi-relational, attention graph-aware framework to detect anti-money laundering and illegal trading activities. On the one hand, a data-driven, graph-aware layer establishes long-term dependencies and correlations between transaction graph nodes. Similarity among graph nodes divides the topological graph into three subgraphs. Learning from these subgraphs and converging nodes enriches local, global, and contextual details. Simultaneously, using repeated nodes across the subgraphs enhances interactivity between them, reduces intra-class ambiguity, and accentuates inter-class differences. On the other hand, a reinforcement learning module embedded in the graph-aware layer compensates for the missing details in node features caused by masking operations. Furthermore, the reconstructed loss function addresses significant classification inaccuracies by reducing the weight assigned to easily classified samples. Balancing these issues and individually supervising each component enables the detection framework to achieve optimal performance. The evaluation results demonstrate that our proposed model exhibits optimal detection performance and robustness, such as F1 of 93.85% and 94.39%. |
| format | Article |
| id | doaj-art-ee350231b29f44b1a4911c0ea74a1df8 |
| institution | Kabale University |
| issn | 2199-4536 2198-6053 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | Springer |
| record_format | Article |
| series | Complex & Intelligent Systems |
| spelling | doaj-art-ee350231b29f44b1a4911c0ea74a1df82025-02-02T12:49:37ZengSpringerComplex & Intelligent Systems2199-45362198-60532024-11-0111111710.1007/s40747-024-01615-9RMGANets: reinforcement learning-enhanced multi-relational attention graph-aware network for anti-money laundering detectionQianyu Wang0Wei-Tek Tsai1Bowen Du2State Key Laboratory of Software Development Environment, Beihang UniversityCollege of Computer and Data Science, Fuzhou UniversityState Key Laboratory of Software Development Environment, Beihang UniversityAbstract Given the anonymity and complexity of illegal transactions, traditional deep-learning methods struggle to establish correlations between transaction addresses, cash flows, and physical users. Additionally, the limited number of labels for illegal transactions results in severe class imbalance and other challenges. To overcome these limitations, we propose a reinforcement learning-enhanced, multi-relational, attention graph-aware framework to detect anti-money laundering and illegal trading activities. On the one hand, a data-driven, graph-aware layer establishes long-term dependencies and correlations between transaction graph nodes. Similarity among graph nodes divides the topological graph into three subgraphs. Learning from these subgraphs and converging nodes enriches local, global, and contextual details. Simultaneously, using repeated nodes across the subgraphs enhances interactivity between them, reduces intra-class ambiguity, and accentuates inter-class differences. On the other hand, a reinforcement learning module embedded in the graph-aware layer compensates for the missing details in node features caused by masking operations. Furthermore, the reconstructed loss function addresses significant classification inaccuracies by reducing the weight assigned to easily classified samples. Balancing these issues and individually supervising each component enables the detection framework to achieve optimal performance. The evaluation results demonstrate that our proposed model exhibits optimal detection performance and robustness, such as F1 of 93.85% and 94.39%.https://doi.org/10.1007/s40747-024-01615-9Anti-money launderingAssociation relationshipsLong-term dependenciesReinforcement learning |
| spellingShingle | Qianyu Wang Wei-Tek Tsai Bowen Du RMGANets: reinforcement learning-enhanced multi-relational attention graph-aware network for anti-money laundering detection Complex & Intelligent Systems Anti-money laundering Association relationships Long-term dependencies Reinforcement learning |
| title | RMGANets: reinforcement learning-enhanced multi-relational attention graph-aware network for anti-money laundering detection |
| title_full | RMGANets: reinforcement learning-enhanced multi-relational attention graph-aware network for anti-money laundering detection |
| title_fullStr | RMGANets: reinforcement learning-enhanced multi-relational attention graph-aware network for anti-money laundering detection |
| title_full_unstemmed | RMGANets: reinforcement learning-enhanced multi-relational attention graph-aware network for anti-money laundering detection |
| title_short | RMGANets: reinforcement learning-enhanced multi-relational attention graph-aware network for anti-money laundering detection |
| title_sort | rmganets reinforcement learning enhanced multi relational attention graph aware network for anti money laundering detection |
| topic | Anti-money laundering Association relationships Long-term dependencies Reinforcement learning |
| url | https://doi.org/10.1007/s40747-024-01615-9 |
| work_keys_str_mv | AT qianyuwang rmganetsreinforcementlearningenhancedmultirelationalattentiongraphawarenetworkforantimoneylaunderingdetection AT weitektsai rmganetsreinforcementlearningenhancedmultirelationalattentiongraphawarenetworkforantimoneylaunderingdetection AT bowendu rmganetsreinforcementlearningenhancedmultirelationalattentiongraphawarenetworkforantimoneylaunderingdetection |