发表机构
University of Houston; Kent State University; PayPal Inc.（休斯顿大学; 肯特州立大学; 贝宝公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对传统风险模型无法捕捉金融网络复杂动态及图神经网络缺乏因果解释的问题，提出因果图X框架，结合图神经网络与反事实推理，能有效评估系统性风险并提供可解释的反事实解释，优于传统和深度学习基线。
AI 中文摘要
全球金融系统的相互联系使其易受系统性风险影响，少数机构的失败可能引发灾难性的级联违约。传统风险模型常无法捕捉这些网络复杂的非线性动态。图神经网络虽能建模关系数据，但主要学习相关模式且像黑箱，无法洞察冲击传播的因果机制。我们引入因果图X，将图神经网络与反事实推理相结合，对系统性风险进行可解释评估。它采用图注意力机制学习机构脆弱性表示，用对抗正则化技术确保这些表示捕捉因果驱动因素而非虚假关联。还提出基于优化的方法生成反事实解释。在大规模合成金融网络上验证，结果表明因果图X在预测级联违约方面显著优于传统和深度学习基线，同时提供稀疏、合理且可操作的反事实解释。
英文摘要
The interconnected nature of global financial systems makes them vulnerable to systemic risks, where the failure of a few institutions can trigger catastrophic cascading defaults. Traditional risk models often fail to capture the complex, non-linear dynamics of these networks. While Graph Neural Networks (GNNs) have shown promise in modeling relational data, they primarily learn correlative patterns and function as black boxes, offering little insight into the causal mechanisms of shock propagation. This limitation is critical for regulators who require explainable models to perform stress tests and devise effective interventions. We introduce CausalGraphX, a novel framework that integrates GNNs with counterfactual reasoning to provide explainable assessments of systemic risk. CausalGraphX employs a Graph Attention mechanism to learn representations of institutional vulnerability and uses an adversarial regularization technique to ensure these representations capture causal drivers rather than spurious correlations. Furthermore, we propose an optimization-based approach to generate counterfactual explanations, answering questions such as, "What minimum capital injection would have prevented Bank A's default under a specific stress scenario?" We validate CausalGraphX on large-scale synthetic financial networks. Our results demonstrate that CausalGraphX significantly outperforms traditional and deep learning baselines in predicting cascading defaults while providing sparse, plausible, and actionable counterfactual explanations.
CommentsAccepted in AAAI'26 Workshop, Agentic AI in Financial Services
