Graph Privacy: A Heterogeneous Federated GNN for Trans-Border Financial Data Circulation
This addresses privacy issues for financial institutions needing to share data across platforms, though it appears incremental as it builds on federated learning and GNNs.
The paper tackles the privacy challenge in sharing financial data across borders by proposing a Heterogeneous Federated Graph Neural Network (HFGNN) to enable data usability without visibility, achieving higher accuracy and faster convergence in simulations compared to existing methods.
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 subgraphs 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.