Identifying Evidence Subgraphs for Financial Risk Detection via Graph Counterfactual and Factual Reasoning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915188187332608 |
|---|---|
| author | Du, Huaming Yuan, Lei Yang, Qing Chen, Xingyan Zhao, Yu Ji, Han Zhuang, Fuzhen Yang, Carl Kou, Gang |
| author_facet | Du, Huaming Yuan, Lei Yang, Qing Chen, Xingyan Zhao, Yu Ji, Han Zhuang, Fuzhen Yang, Carl Kou, Gang |
| contents | Company financial risks pose a significant threat to personal wealth and national economic stability, stimulating increasing attention towards the development of efficient andtimely methods for monitoring them. Current approaches tend to use graph neural networks (GNNs) to model the momentum spillover effect of risks. However, due to the black-box nature of GNNs, these methods leave much to be improved for precise and reliable explanations towards company risks. In this paper, we propose CF3, a novel Counterfactual and Factual learning method for company Financial risk detection, which generates evidence subgraphs on company knowledge graphs to reliably detect and explain company financial risks. Specifically, we first propose a meta-path attribution process based on Granger causality, selecting the meta-paths most relevant to the target node labels to construct an attribution subgraph. Subsequently, we propose anedge-type-aware graph generator to identify important edges, and we also devise a layer-based feature masker to recognize crucial node features. Finally, we utilize counterfactual-factual reasoning and a loss function based on attribution subgraphs to jointly guide the learning of the graph generator and feature masker. Extensive experiments on three real-world datasets demonstrate the superior performance of our method compared to state-of-the-art approaches in the field of financial risk detection. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_06441 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Identifying Evidence Subgraphs for Financial Risk Detection via Graph Counterfactual and Factual Reasoning Du, Huaming Yuan, Lei Yang, Qing Chen, Xingyan Zhao, Yu Ji, Han Zhuang, Fuzhen Yang, Carl Kou, Gang Computational Engineering, Finance, and Science Company financial risks pose a significant threat to personal wealth and national economic stability, stimulating increasing attention towards the development of efficient andtimely methods for monitoring them. Current approaches tend to use graph neural networks (GNNs) to model the momentum spillover effect of risks. However, due to the black-box nature of GNNs, these methods leave much to be improved for precise and reliable explanations towards company risks. In this paper, we propose CF3, a novel Counterfactual and Factual learning method for company Financial risk detection, which generates evidence subgraphs on company knowledge graphs to reliably detect and explain company financial risks. Specifically, we first propose a meta-path attribution process based on Granger causality, selecting the meta-paths most relevant to the target node labels to construct an attribution subgraph. Subsequently, we propose anedge-type-aware graph generator to identify important edges, and we also devise a layer-based feature masker to recognize crucial node features. Finally, we utilize counterfactual-factual reasoning and a loss function based on attribution subgraphs to jointly guide the learning of the graph generator and feature masker. Extensive experiments on three real-world datasets demonstrate the superior performance of our method compared to state-of-the-art approaches in the field of financial risk detection. |
| title | Identifying Evidence Subgraphs for Financial Risk Detection via Graph Counterfactual and Factual Reasoning |
| topic | Computational Engineering, Finance, and Science |
| url | https://arxiv.org/abs/2503.06441 |