LightTR: A Lightweight Framework for Federated Trajectory Recovery
Ziqiao Liu, Hao Miao, Yan Zhao, Chenxi Liu, Kai Zheng, Huan Li
TL;DR
LightTR tackles privacy-preserving trajectory recovery for decentralized, low-sampling-rate trajectories by coupling a lightweight local trajectory embedding module with a meta-knowledge enhanced local-global training paradigm in horizontal federated learning. It replaces expensive spatio-temporal operators with a compact ML-based pipeline and uses a teacher-student distillation mechanism to accelerate convergence and reduce communication overhead. Evaluations on Geolife and Tdrive show LightTR achieving state-of-the-art accuracy with substantially lower computation and communication costs than centralized baselines and other FL approaches, demonstrating strong robustness to data heterogeneity. The framework enables scalable, privacy-preserving trajectory recovery suitable for urban sensing and smart mobility applications.
Abstract
With the proliferation of GPS-equipped edge devices, huge trajectory data is generated and accumulated in various domains, motivating a variety of urban applications. Due to the limited acquisition capabilities of edge devices, a lot of trajectories are recorded at a low sampling rate, which may lead to the effectiveness drop of urban applications. We aim to recover a high-sampled trajectory based on the low-sampled trajectory in free space, i.e., without road network information, to enhance the usability of trajectory data and support urban applications more effectively. Recent proposals targeting trajectory recovery often assume that trajectories are available at a central location, which fail to handle the decentralized trajectories and hurt privacy. To bridge the gap between decentralized training and trajectory recovery, we propose a lightweight framework, LightTR, for federated trajectory recovery based on a client-server architecture, while keeping the data decentralized and private in each client/platform center (e.g., each data center of a company). Specifically, considering the limited processing capabilities of edge devices, LightTR encompasses a light local trajectory embedding module that offers improved computational efficiency without compromising its feature extraction capabilities. LightTR also features a meta-knowledge enhanced local-global training scheme to reduce communication costs between the server and clients and thus further offer efficiency improvement. Extensive experiments demonstrate the effectiveness and efficiency of the proposed framework.