TY - GEN
T1 - Risk-Aware Graph Neural Networks for Financial Fraud Detection
AU - Wang, Xinyu
AU - Zhang, Yongqi
AU - Yan, Bo
AU - Gao, Chunxiao
AU - Su, Hongyi
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2027.
PY - 2027
Y1 - 2027
N2 - Financial fraud detection is critical due to expanding digital payment and increasingly sophisticated fraud. Existing Graph Neural Network (GNN) based methods face the risk signal dilution during message propagation caused by feature camouflage. To address this, we propose a Risk-Aware Graph Neural Network (RA-GNN) which explicitly models risk propagation via multi-source risk extraction and adaptive fusion, a risk-aware attention mechanism that incorporates risk scores as bias terms, a risk-gated unit that dynamically updates risk states across layers, and a masked semi-supervised training strategy that masks center node label embeddings while retaining neighbors’, forcing the model to infer risk from local graph context. Extensive experiments on three real-world datasets demonstrate that RA-GNN consistently outperforms state-of-the-art baselines across AUC, F1, and AP metrics, achieving a 13.3% relative improvement in AP on YelpChi. Ablation studies confirm the contribution of each core component.
AB - Financial fraud detection is critical due to expanding digital payment and increasingly sophisticated fraud. Existing Graph Neural Network (GNN) based methods face the risk signal dilution during message propagation caused by feature camouflage. To address this, we propose a Risk-Aware Graph Neural Network (RA-GNN) which explicitly models risk propagation via multi-source risk extraction and adaptive fusion, a risk-aware attention mechanism that incorporates risk scores as bias terms, a risk-gated unit that dynamically updates risk states across layers, and a masked semi-supervised training strategy that masks center node label embeddings while retaining neighbors’, forcing the model to infer risk from local graph context. Extensive experiments on three real-world datasets demonstrate that RA-GNN consistently outperforms state-of-the-art baselines across AUC, F1, and AP metrics, achieving a 13.3% relative improvement in AP on YelpChi. Ablation studies confirm the contribution of each core component.
KW - Graph Neural Networks
KW - financial fraud detection
KW - risk-aware learning
UR - https://www.scopus.com/pages/publications/105046448202
U2 - 10.1007/978-981-92-3400-4_29
DO - 10.1007/978-981-92-3400-4_29
M3 - Conference contribution
AN - SCOPUS:105046448202
SN - 9789819233991
T3 - Lecture Notes in Computer Science
SP - 348
EP - 359
BT - Advanced Intelligent Computing Technology and Applications - 22nd International Conference on Intelligent Computing, Proceedings
A2 - Huang, De-Shuang
A2 - Zhang, Qinhu
A2 - Pan, Yijie
A2 - Zhang, Chuanlei
A2 - Chen, Wei
A2 - Li, Bo
A2 - Bao, Wenzheng
A2 - Premaratne, Prashan
PB - Springer Science and Business Media Deutschland GmbH
T2 - 22nd International Conference on Intelligent Computing, ICIC 2026
Y2 - 22 July 2026 through 26 July 2026
ER -