Partial Federated Learning

arXiv:2403.01615v1 Announce Type: new
Abstract: Federated Learning (FL) is a popular algorithm to train machine learning models on user data constrained to edge devices (for example, mobile phones) due to privacy concerns. Typically, FL is trained with the assumption that no part of the user data can be egressed from the edge. However, in many production settings, specific data-modalities/meta-data are limited to be on device while others are not. For example, in commercial SLU systems, it is typically desired to …

abstract algorithm arxiv concerns cs.dc cs.lg data devices edge edge devices example federated learning machine machine learning machine learning models mobile mobile phones part phones popular privacy production the edge train type user data