Multi-Task Model Personalization for Federated Supervised SVM in Heterogeneous Networks

no code implementations • 17 Mar 2023 • Aleksei Ponomarenko-Timofeev, Olga Galinina, Ravikumar Balakrishnan, Nageen Himayat, Sergey Andreev, Yevgeni Koucheryavy

The proposed method utilizes efficient computations and model exchange in a network of heterogeneous nodes and allows personalization of the learning model in the presence of non-i. i. d.

Multi-Task Learning regression