Graph Privacy: A Heterogeneous Federated GNN for Trans-Border Financial Data Circulation

The sharing of external data has become a strong demand of financial institutions, but the privacy issue has led to the difficulty of interconnecting different platforms and the low degree of data openness. To effectively solve the privacy problem of financial data in trans-border flow and sharing, to ensure that the data is'available but not visible', to realize the joint portrait of all kinds of heterogeneous data of business organizations in different industries, we propose a Heterogeneous Federated Graph Neural Network (HFGNN) approach. In this method, the distribution of heterogeneous business data of trans-border organizations is taken as subgraphs, and the sharing and circulation process among subgraphs is constructed as a statistically heterogeneous global graph through a central server. Each subgraph learns the corresponding personalized service model through local training to select and update the relevant subset of sub-graphs with aggregated parameters, and effectively separates and combines topological and feature information among subgraphs. Finally, our simulation experimental results show that the proposed method has higher accuracy performance and faster convergence speed than existing methods. 1 Introduction With the continuous advancement of financial technology's profound empowerment of business, the shared application of external data (such as Internet companies, insurance companies, and other third-party data providers) has become a strong demand for financial institutions. Financial risk control and customer acquisition based on privacy computing have become the most important privacy computing implementation scenario at present [ Oyewole et al., 2024; Farayola et al., 2024 ] . However, there are three main risks in the current cooperation process between financial institutions and external data sources: first, it involves a large amount of personal user information and is subject to strict regulatory requirements; second, the data assets and trade secrets Corresponding author accumulated by the institution's own business are easy to be leaked; Third, because the data itself can be copied and easily spread, and once shared cannot be traced, the confirmation of data assets is difficult, and commercialization is seriously restricted[ Christian, 2024 ] .