no code implementations • 19 Jan 2024 • Pouya M. Ghari, Yanning Shen
Although employing a larger set of candidate models naturally leads to more flexibility in model selection, this may be infeasible in cases where prediction tasks are performed on edge devices with limited memory.
1 code implementation • 9 Nov 2023 • Pouya M. Ghari, Yanning Shen
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.