Empowering Credit Risk Detection in Weixin Pay with Billion-Scale Deep Graph Learning

2026-08-03

AI Summary

This work addresses the challenges of scalability and fragmented risk evidence chains in credit fraud detection within heterogeneous user–risk graphs at billion-user scale. To this end, we propose a risk-aware overlapping subgraph learning framework that integrates load-balanced base partitioning with budget-constrained sampling of long-tail nodes, effectively preserving critical risk propagation paths while suppressing noise. Furthermore, we introduce a cross-subgraph consistency alignment mechanism to mitigate inconsistencies in local representations. Experiments on WeChat Pay’s production dataset demonstrate that the proposed framework significantly improves detection accuracy while maintaining strong scalability, thereby effectively supporting risk control demands in ultra-large-scale financial ecosystems.

Abstract

Credit risk detection, particularly mitigating individual fraud, is crucial for maintaining the stability of digital financial ecosystems. Accurately identifying credit fraud among billions of users is critical for minimizing financial losses and safeguarding the sustainability of inclusive financial services. Given that credit fraud risks are often concealed within heterogeneous user-risk graphs, Graph Neural Networks (GNNs) have emerged as an effective tool for risk mining by capturing complex dependencies. To address the scalability bottleneck of industrial GNNs, distributed training based on subgraphs is indispensable. However, existing strategies often compromise topological integrity for load balancing. This can be catastrophic for risk detection, as it indiscriminately severs the long-tail evidence chains essential for risk propagation. Overlapping subgraphs can restore severed risk contexts but inevitably introduce redundancy and noise, while overlooking the representation alignment across different local subgraphs. In this paper, we propose a risk-aware overlapping subgraph learning framework for large-scale credit risk detection. We first construct base partitions to ensure load balance. Then, we perform budget-constrained sampling that selects informative long-tail nodes, thereby preserving critical risk diffusion patterns while filtering out noise. To mitigate representation inconsistency, we design a cross-subgraph consistency alignment mechanism. By enforcing alignment constraints on the overlapping nodes, we harmonize the local representations into a globally consistent latent space. Extensive experiments on Weixin Pay's production dataset demonstrate that our model significantly outperforms existing strategies for risk detection, offering a scalable and effective solution for industrial graph learning.

Problem

• credit risk detection
• graph neural networks
• distributed training
• subgraph partitioning
• risk propagation

Innovation

• risk-aware overlapping subgraph
• budget-constrained sampling
• cross-subgraph consistency alignment
• large-scale GNN
• credit risk detection