用可解释图神经网络监测美国银行系统风险，提前预警危机。
Explainable Graph Neural Networks for Interbank Contagion Surveillance: A Regulatory-Aligned Framework for the U.S. Banking Sector
- 构建动态加权银行间借贷图，融合时空注意力机制
- 在8103家银行数据上实现0.939的AUPRC，接近最优模型
- 识别出资产回报率和不良贷款率是关键预警指标
本文提出时空图注意力网络（ST-GAT）框架，用于对美国银行业间系统性风险进行早期预警与宏观审慎监管。该框架基于58个季度（2010Q1–2024Q2）的8,103家联邦存款保险公司（FDIC）承保机构数据，利用最大熵估计重构双边敞口，构建动态有向加权图。模型在所有GNN架构中表现最佳，AUPRC达0.939±0.010，仅略低于XGBoost的0.944。消融实验表明，BiLSTM时间模块贡献+0.020 AUPRC；时间注意力权重呈单调递减，符合长期结构性脆弱性特征。置换重要性分析显示，资产回报率（ROA，0.309）和不良贷款率（NPL Ratio，0.252）为关键预测因子，与2023年区域性银行危机事后分析一致。所有数据来自公开的FDIC Call Reports与FRED系列，代码与结果均已开源。
原文摘要 · Abstract (English)
The Spatial-Temporal Graph Attention Network (ST-GAT) framework was created to serve as an explainable GNN-based solution for detecting bank distress early warning signs and for conducting macro-prudential surveillance of the interbank system in the United States. The ST-GAT framework models 8,103 FDIC insured institutions across 58 quarterly snapshots (2010Q1-2024Q2). Bilateral exposures were reconstructed from publicly available FDIC Call Reports using maximum entropy estimation to produce a dynamic directed weighted graph. The framework achieves the highest AUPRC among all GNN architectures (0.939 +/- 0.010), trailing only XGBoost (0.944). Ablation analysis confirms the BiLSTM temporal component contributes +0.020 AUPRC; temporal attention weights exhibit a monotonically decreasing pattern consistent with long-run structural vulnerability weighting. Permutation importance identifies ROA (0.309) and NPL Ratio (0.252) as dominant predictors, consistent with post-mortem analyses of the 2023 regional banking crisis. All data are publicly available FDIC Call Reports and FRED series; all code and results are released.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。