Multi-Level Federated Graph Learning and Self-Attention Based Personalized Wi-Fi Indoor Fingerprint Localization

Deep learning-based Wi-Fi indoor fingerprint localization, which requires a large received signal strength (RSS) dataset for training, has been widely studied. Federated learning (FL) is recently introduced into indoor localization in order to address the problem of data sharing without privacy disclosure. However, under the serious data heterogeneity of FL, the averaged model will perform worse for individual client. In this letter, a multi-level federated graph learning and self-attention based personalized indoor localization method is proposed to further capture the intrinsic features of RSS, and learn the aggregation manner of shared information uploaded by clients, with better personalization accuracy. The experimental results demonstrate that proposed methods achieve a higher personalized localization accuracy than compared personalized federated learning (PFL) methods, in most of the simulation settings.