The credit risk of enterprise groups is gradually characterized by network transmission, and the traditional model with the financial indicators of a single enterprise as the core is difficult to describe the impact of equity, guarantee, related party transactions and other relationships on risk diffusion. Based on multi-source public data such as CSMAR, Tianyancha, and China Execution Information Disclosure Network, this study empirically constructs a real enterprise association knowledge graph, and designs a heterogeneous graph neural network credit risk transmission early warning model. The model takes enterprises, natural persons, financial institutions and risk events as nodes, takes equity, guarantees, related party transactions and senior executive positions as the edges, integrates the characteristics of finance, justice, rating and public opinion, and aggregates neighbor risk information through the relational attention mechanism. The results showed that the AUC of the KG-GNN model reached 0.92, which was better than the Logistic regression, XGBoost and basic GCN models in terms of F1-Score, Recall and KS. The ablation experiment shows that the relationship between equity and guarantee is the key relationship type in the transmission of group credit risk. The results show that the framework can identify the external infectious pressure that has not yet been shown in the monolithic report, and can provide a reference for the credit management and penetrating risk control of group customers.

Wei Sun. Research on Early Warning Model of Credit Risk Transmission of Enterprise Group Based on Graph Neural Network and Knowledge Graph. International Journal of Neural Network (2026), Vol. 5, Issue 1: 52-63. https://doi.org/10.38007/NN.2026.050106.

[1] Liu, X., & Yang, D. (2025, March). LLM Data Strategy: Improving Data Availability and Efficiency. In Doctoral Symposium on Computational Intelligence (pp. 425-437). Singapore: Springer Nature Singapore.

[2] Zhang, Q. (2025, October). Application of Reinforcement Learning in Dynamic Advertising Content Generation. In 2025 2nd International Conference on Software, Systems and Information Technology (SSITCON) (pp. 1-5). IEEE.

[3] Zhang, Q. (2026). Security Improvement and Application of Identity and Access Management in Saas Platform.

[4] Yanchun Wang. (2025) Research on Enhancing ERP System Efficiency Through AI in Cross-border Supply Chain Environments. Advances in Computer and Communication, 6(5), 268-273.

[5] Wu, Y. (2025, October). Multi-Level Belief Rule Base Modeling Architecture and Intelligent Optimization Technology for Decision Support Systems. In 2025 2nd International Conference on Software, Systems and Information Technology (SSITCON) (pp. 1-8). IEEE.

[6] Zhang, C., Han, J., Zou, Y., Dong, K., Li, Y., Ding, J., & Han, X. (2024, April). Detecting the anomalies in LiDAR pointcloud. In WCX SAE World Congress Experience. SAE Technical Paper.

[7] Chen, M. (2026). Research on Privacy-Preserving AI Model Training and Validation Methods Based on Federated Learning.

[8] Yanchun Wang. (2025) Research on Enhancing ERP System Efficiency Through AI in Cross-border Supply Chain Environments. Advances in Computer and Communication, 6(5), 268-273.

[9] Zhou, Y. (2026). Energy efficiency and sustainability strategies for data centers. European Journal of Engineering and Technologies, 2(1), 46-53.

[10] Yiting Hong. Differentially Private High-Dimensional Business Data Publishing and Analysis Algorithm. International Journal of Business Management and Economics and Trade (2026), Vol. 7, Issue 1: 28-35.

[11] Xu, D. (2026). Analysis of the impact of video infrastructure optimization on large-scale content quality improvement.

[12] Ding, J. (2025). Research On CODP Localization Decision Model Of Automotive Supply Chain Based On Delayed Manufacturing Strategy. arXiv preprint arXiv:2511.05899.

[13] Pan, H. (2025, March). Research on Efficient Computing Model of Hartree Fock and Density Functional Theory Based on GPU Acceleration. In Doctoral Symposium on Computational Intelligence (pp. 485-496). Singapore: Springer Nature Singapore.

[14] Wu, W. (2025, June). Construction and optimization of intelligent gateway software management platform based on jenkins cluster management under cloud edge integration architecture in industrial internet of things. In International Conference on 6G Communications Networking and Signal Processing (pp. 633-645). Singapore: Springer Nature Singapore.

[15] Huang, J. (2025, August). Research on Multi-Model Fusion Machine Learning Demand Intelligent Forecasting System in Cloud Computing Environment. In 2025 2nd International Conference on Intelligent Algorithms for Computational Intelligence Systems (IACIS) (pp. 1-7). IEEE.

[16] Hou, Y. (2026). Exploration of Data Center Cost Optimization Pathways Under Multi-generation CPU and GPU Collaborative Architectures. Engineering Advances, 6(1).

[17] Wu Y. Software Engineering Practice of Microservice Architecture in Full Stack Development: From Architecture Design to Performance Optimization[J]. 2025.

[18] Wu Y. Optimization of Generative AI Intelligent Interaction System Based on Adversarial Attack Defense and Content Controllable Generation[J]. 2025.

[19] Hou, Y. (2026). Research on Heterogeneous Server Upgrade Strategies and Resource Utilization Efficiency Oriented Toward Green Computing Objectives. Advances in Computer and Communication, 7(1).

[20] Wu Y. Software Engineering Practice of Microservice Architecture in Full Stack Development: From Architecture Design to Performance Optimization[J]. 2025.

[21] Sun J. Quantile Regression Study on the Impact of Investor Sentiment on Financial Credit from the Perspective of Behavioral Finance[J]. 2025.

[22] Wang Y. Application of Data Completion and Full Lifecycle Cost Optimization Integrating Artificial Intelligence in Supply Chain[J]. 2025.

[23] Sun, J. (2025). Research on Business Data-driven Risk Prediction Methods Based on Machine Learning. Advances in Computer and Communication, 6(4).

[24] Chen M. Research on Automated Risk Detection Methods in Machine Learning Integrating Privacy Computing[J]. 2025.

[25] Wu, Y. (2026). Federated Learning-based Algorithm Design for Privacy Preservation in Cross-domain Data Sharing. Engineering Advances, 6(1).

[26] Ding, J. (2025). Exploration of Process Improvement in Automotive Manufacturing Based on Intelligent Production. International Journal of Engineering Advances, 2(2), 17-23.

[27] Huang, J. (2025, September). Performance Evaluation Index System and Engineering Best Practice of Production-Level Time Series Machine Learning System. In 2025 International Conference on Intelligent Communication Networks and Computational Techniques (ICICNCT) (pp. 01-07). IEEE.