Skip to yearly menu bar Skip to main content


Federated Learning with Partial Model Personalization

Krishna Pillutla · Kshitiz Malik · Abdel-rahman Mohamed · Michael Rabbat · Maziar Sanjabi · Lin Xiao

Hall E #724

Keywords: [ OPT: Non-Convex ] [ OPT: Large Scale, Parallel and Distributed ]


We consider two federated learning algorithms for training partially personalized models, where the shared and personal parameters are updated either simultaneously or alternately on the devices. Both algorithms have been proposed in the literature, but their convergence properties are not fully understood, especially for the alternating variant. We provide convergence analyses of both algorithms in the general nonconvex setting with partial participation and delineate the regime where one dominates the other. Our experiments on real-world image, text, and speech datasets demonstrate that (a) partial personalization can obtain most of the benefits of full model personalization with a small fraction of personal parameters, and, (b) the alternating update algorithm outperforms the simultaneous update algorithm by a small but consistent margin.

Chat is not available.