The classifier judged this item not relevant to AI security, so it is left out of lists, feeds, the API and dataset releases. If that is wrong, report a correction on this page.
InfoResearchPeer-reviewed
FedNK-RF: Federated Kernel Learning With Heterogeneous Data and Optimal Rates
- Published
- Record updated
Summary
The authors propose FedK-RF, a federated kernel learning algorithm that shares random features of local data subsets to improve predictive accuracy under data heterogeneity while protecting privacy. They extend it to FedNK-RF, which adds a federated Nyström approximation to reduce errors from random features, and derive excess risk bounds with minimax optimal rates using integral operator theory. Experiments are reported to show FedNK-RF's superiority.