Federated Learning With Experience-Driven Model Migration in Heterogeneous Edge Networks
Jianchun Liu, Shilong Wang, Hongli Xu, Yang Xu, Yunming Liao, Jinyang Huang, He Huang
Abstract
To approach the challenges of non-IID data and limited communication resource raised by the emerging federated learning (FL) in mobile edge computing (MEC), we propose an efficient framework, called <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">FedMigr</i> , which integrates a deep reinforcement learning (DRL) based model migration strategy into the pioneer FL algorithm <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">FedAvg</i> . According to the data distribution and resource budgets, our <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">FedMigr</i> will intelligently guide one client to forward its local model to another client after local updating, before directly sending the local models to the server for global aggregation as in <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">FedAvg</i> . Intuitively, migrating a local model from one client to another is equivalent to training the model over more data from different clients, alleviating the influence of non-IID issue. To this end, we propose an experience-driven method to make proper decisions for model migrations while satisfying the resource constraints. We also prove that <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">FedMigr</i> can help to reduce the parameter divergences between different local models and the global model from a theoretical perspective under the non-IID setting. Extensive experiments on three popular benchmark datasets demonstrate that <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">FedMigr</i> can achieve an average accuracy improvement of around 13%, and reduce bandwidth consumption for global communication by 42% on average, compared with the baselines.