Trajectory-User Linking via Multi-Scale Graph Attention Network

Yujie Li, Tao Sun, Zezhi Shao, Yiqiang Zhen, Yongjun Xu, Fei Wang

Abstract: Highlights•A multi-scale graph attention network for effective and efficient trajectory user linking•A graph construction method preserves the original trajectory context of arbitrary length.•A spatio-temporal network mines human mobility patterns in parallel and robustly.•Sufficient experiments prove its better performance and module validity.