Self-supervised Trajectory Representation Learning with Temporal Regularities and Travel Semantics
arXiv (Cornell University)(2022)
摘要
Trajectory Representation Learning (TRL) is a powerful tool for
spatial-temporal data analysis and management. TRL aims to convert complicated
raw trajectories into low-dimensional representation vectors, which can be
applied to various downstream tasks, such as trajectory classification,
clustering, and similarity computation. Existing TRL works usually treat
trajectories as ordinary sequence data, while some important spatial-temporal
characteristics, such as temporal regularities and travel semantics, are not
fully exploited. To fill this gap, we propose a novel Self-supervised
trajectory representation learning framework with TemporAl Regularities and
Travel semantics, namely START. The proposed method consists of two stages. The
first stage is a Trajectory Pattern-Enhanced Graph Attention Network (TPE-GAT),
which converts the road network features and travel semantics into
representation vectors of road segments. The second stage is a Time-Aware
Trajectory Encoder (TAT-Enc), which encodes representation vectors of road
segments in the same trajectory as a trajectory representation vector,
meanwhile incorporating temporal regularities with the trajectory
representation. Moreover, we also design two self-supervised tasks, i.e.,
span-masked trajectory recovery and trajectory contrastive learning, to
introduce spatial-temporal characteristics of trajectories into the training
process of our START framework. The effectiveness of the proposed method is
verified by extensive experiments on two large-scale real-world datasets for
three downstream tasks. The experiments also demonstrate that our method can be
transferred across different cities to adapt heterogeneous trajectory datasets.
更多查看译文
关键词
complicated raw trajectories,downstream tasks,heterogeneous trajectory datasets,low-dimensional representation vectors,novel Self-supervised trajectory representation,ordinary sequence data,road segments,self-supervised tasks,span-masked trajectory recovery,spatial-temporal characteristics,spatial-temporal data analysis,temporal regularities,Time-Aware Trajectory Encoder,trajectory classification,trajectory contrastive learning,Trajectory Pattern-Enhanced Graph Attention Network,Trajectory Representation Learning,trajectory representation vector,travel semantics,TRL works
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要