Efficient Vertical Federated Learning with Secure Aggregation. (arXiv:2305.11236v1 [cs.LG])

The majority of work in privacy-preserving federated learning (FL) has been
focusing on horizontally partitioned datasets where clients share the same sets
of features and can train complete models independently. However, in many
interesting problems, such as financial fraud detection and disease detection,
individual data points are scattered across different clients/organizations in
vertical federated learning. Solutions for this type of FL require the exchange
of gradients between participants and rarely consider privacy and security
concerns, posing a potential risk of …

aggregation clients data data points datasets detection disease features federated learning financial financial fraud fraud fraud detection organizations privacy problems share train work