Joint Scheduling and Robust Aggregation for Federated Localization Over Unreliable Wireless D2D Networks

Deep learning-assisted indoor fingerprint localization based on frequent data collection is motivating renewed interest via crowdsourcing. Uploading raw training data may cause exposure of privacy in crowdsourcing. Federated Learning (FL) is thus introduced into indoor localization since its advantages in privacy protection. Nevertheless, most current FL-based indoor localization studies do not consider deploying systems in real wireless environments. Furthermore, transmission latency and outages caused by unreliable wireless networks are ignored. In addition, centralized FL-based indoor localization is adopted in most studies while decentralized FL-based indoor localization system is seldomly considered. In this paper, a decentralized Federated Learning (DFL)-based indoor localization system over wireless D2D networks is proposed for mitigating effects from single point of failure and communication bottleneck from centralized FL. Moreover, unreliable wireless links are further considered. To reduce the transmission latency, a greedy-based scheduling policy is devised to select DFL participants via jointly considering channel condition and scheduling fairness. For the possible transmission outages, a maximum distribution similarity-based successive model decoding aggregation algorithm is proposed to aggregate models more robustly and the corresponding theoretical analysis is provided. Experimental results based on real-world dataset collected by us show that proposed methods achieve better performance both in reducing latency and localization error than baseline schemes.