TY - GEN
T1 - FDFRL
T2 - 34th International Conference on Artificial Neural Networks, ICANN 2025
AU - Zhang, Nana
AU - Li, Qin
AU - Zhu, Kun
AU - Zhu, Dandan
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.
PY - 2026
Y1 - 2026
N2 - To tackle extreme class imbalance, non-independent and identically (non-IID) distributed transactions and dynamic fraud patterns in credit card fraud detection (CCFD), we propose FDFRL, credit card Fraud Detection based on Federated Reinforcement Learning, with three core modules: Kernel-guided adversarial representation learning for high-fidelity synthetic sample generation and robust feature embeddings via hierarchical adversarial refinement. PPO-based federated reinforcement learning employing gradient smoothing and dynamic weighting to harmonize updates from heterogeneous clients and ensure steady convergence. Label-driven federated fusion module that seamlessly integrates local representations into a unified global classifier. Extensive experiments on real-world fraud datasets show that FDFRL markedly outperforms eight state-of-the-art baselines.
AB - To tackle extreme class imbalance, non-independent and identically (non-IID) distributed transactions and dynamic fraud patterns in credit card fraud detection (CCFD), we propose FDFRL, credit card Fraud Detection based on Federated Reinforcement Learning, with three core modules: Kernel-guided adversarial representation learning for high-fidelity synthetic sample generation and robust feature embeddings via hierarchical adversarial refinement. PPO-based federated reinforcement learning employing gradient smoothing and dynamic weighting to harmonize updates from heterogeneous clients and ensure steady convergence. Label-driven federated fusion module that seamlessly integrates local representations into a unified global classifier. Extensive experiments on real-world fraud datasets show that FDFRL markedly outperforms eight state-of-the-art baselines.
KW - Dynamic Fraud Patterns
KW - Extreme Class Imbalance
KW - Federated Reinforcement Learning
KW - Proximal Policy Optimization
KW - Transaction Fraud Detection
UR - https://www.scopus.com/pages/publications/105016642573
U2 - 10.1007/978-3-032-04555-3_27
DO - 10.1007/978-3-032-04555-3_27
M3 - 会议稿件
AN - SCOPUS:105016642573
SN - 9783032045546
T3 - Lecture Notes in Computer Science
SP - 326
EP - 338
BT - Artificial Neural Networks and Machine Learning – ICANN 2025 - 34th International Conference on Artificial Neural Networks, 2025, Proceedings
A2 - Senn, Walter
A2 - Sanguineti, Marcello
A2 - Saudargiene, Ausra
A2 - Tetko, Igor V.
A2 - Villa, Alessandro E. P.
A2 - Jirsa, Viktor
A2 - Bengio, Yoshua
PB - Springer Science and Business Media Deutschland GmbH
Y2 - 9 September 2025 through 12 September 2025
ER -