Federated Learning (FL) is emerging as a promising technology to build machine learning models in a decentralized, privacy-preserving fashion . FL enables local training on user devices, avoiding user data to be transferred to centralized servers . FLaaS can be deployed in different operational environments, such as mobile phones and 3rd-party applications, it has been recently deployed in real systems, but the possibility of collaborative modeling across different 3rd party applications has not yet been explored . We present a system enabling different scenarios of collaborative model building and addressing the challenges of permission and privacy management, usability, and model training . We demonstrate FLaa’s feasibility in building unique or joint FL models across applications for image objectdetection in a few hours, across 100 devices, using a mobile phone setting, in a test of FLaa

Author(s) : Nicolas Kourtellis, Kleomenis Katevas, Diego Perino

Links : PDF - Abstract

Code :

Keywords : learning - fl - applications - party - flaa -

Leave a Reply

Your email address will not be published. Required fields are marked *