Personalized Online Federated Learning with Multiple Kernels
This work addresses challenges in federated learning for non-linear function approximation, offering a personalized solution for clients with heterogeneous data, though it appears incremental as it builds on existing multi-kernel and federated learning techniques.
The paper tackled communication efficiency and data heterogeneity in online federated multi-kernel learning by proposing a scalable algorithm using random feature approximation, achieving sub-linear regret for each client and showing advantages over other methods in experiments on real datasets.
Multi-kernel learning (MKL) exhibits well-documented performance in online non-linear function approximation. Federated learning enables a group of learners (called clients) to train an MKL model on the data distributed among clients to perform online non-linear function approximation. There are some challenges in online federated MKL that need to be addressed: i) Communication efficiency especially when a large number of kernels are considered ii) Heterogeneous data distribution among clients. The present paper develops an algorithmic framework to enable clients to communicate with the server to send their updates with affordable communication cost while clients employ a large dictionary of kernels. Utilizing random feature (RF) approximation, the present paper proposes scalable online federated MKL algorithm. We prove that using the proposed online federated MKL algorithm, each client enjoys sub-linear regret with respect to the RF approximation of its best kernel in hindsight, which indicates that the proposed algorithm can effectively deal with heterogeneity of the data distributed among clients. Experimental results on real datasets showcase the advantages of the proposed algorithm compared with other online federated kernel learning ones.