Are You Left Out? An Efficient and Fair Federated Learning for Personalized Profiles onWearable Devices of Inferior Networking Conditions

Abstract

Wearable computers engage in percutaneous interactions with human users and revolutionize the way of learning human activities. Due to rising privacy concerns, federated learning has been recently proposed to train wearable data with privacy preservation collaboratively. However, under the state-of-the-art (SOTA) schemes, user profiles on wearable devices of inferior networking conditions are regarded as `left out'. Such schemes suffer from three fundamental limitations: (1) the widely adopted network-capacity-based client selection leads to biased training; (2) the aggregation has low communication efficiency; (3) users lack convenient channels for providing feedback on wearable devices. Therefore, this paper proposes a Fair and Communication-efficient Federated Learning scheme, namely FCFL. FCFL is a full-stack learning system specifically designed for wearable computers, improving the SOTA performance in terms of communication efficiency, fairness, personalization, and user experience. To this end, we design a technique named ThrowRightAway (TRA) to loose the network capacity constraints. Clients with poor networks are allowed to be selected as participators to improve the representation and guarantee the model's fairness. Remarkably, we propose Movement Aware Federated Learning (MAFL) to aggregate only the model updates with top contributions to the global model for the sake of communication efficiency. Accordingly, we implemented an FCFL-supported prototype as a sports application on smartwatches. Our comprehensive evaluation demonstrated that FCFL is a communication efficient scheme significantly reducing uploaded data by up to 29.77%, with a prominent feature of guaranteeing enhanced fairness up to 65.07%. Also, FCFL achieves robust personalization performance (i.e., 20% improvements of global model accuracy) in the face of packet loss below a certain fraction (10%-30%). A follow-up user survey shows that our FCFL-supported prototypical system on wearable devices significantly reduces users' workload.