Privacy-preserving design of graph neural networks with applications to vertical federated learning

• Published in: arXiv.org
• Main Authors: Wu, Ruofan, Zhang, Mingyang, Lyu, Lingjuan, Xu, Xiaolong, Hao, Xiuquan, Fu, Xinyi, Liu, Tengfei, Zhang, Tianyi, Wang, Weiqiang
• Format: Paper
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 31.10.2023
• Subjects: Datasets; Graph neural networks; Graph representations; Graphical representations; Graphs; Machine learning; Message passing; Privacy; Privatization; Risk management; Structured data

The paradigm of vertical federated learning (VFL), where institutions collaboratively train machine learning models via combining each other's local feature or label information, has achieved great success in applications to financial risk management (FRM). The surging developments of graph rep...