Grid and Road Expressions Are Complementary for Trajectory Representation Learning

TL;DR

This paper introduces GREEN, a multimodal trajectory representation learning method that combines grid and road trajectory data using contrastive and MLM losses, significantly improving downstream task performance.

Contribution

GREEN is the first to jointly utilize grid and road trajectory data with tailored encoders and a dual-modal fusion, enhancing trajectory representations.

Findings

GREEN outperforms 7 state-of-the-art methods across three tasks.

GREEN improves baseline accuracy by an average of 15.99%.

The multimodal approach effectively captures complementary trajectory information.

Abstract

Trajectory representation learning (TRL) maps trajectories to vectors that can be used for many downstream tasks. Existing TRL methods use either grid trajectories, capturing movement in free space, or road trajectories, capturing movement in a road network, as input. We observe that the two types of trajectories are complementary, providing either region and location information or providing road structure and movement regularity. Therefore, we propose a novel multimodal TRL method, dubbed GREEN, to jointly utilize Grid and Road trajectory Expressions for Effective representatioN learning. In particular, we transform raw GPS trajectories into both grid and road trajectories and tailor two encoders to capture their respective information. To align the two encoders such that they complement each other, we adopt a contrastive loss to encourage them to produce similar embeddings for the same raw trajectory and design a mask language model (MLM) loss to use grid trajectories to help reconstruct masked road trajectories. To learn the final trajectory representation, a dual-modal interactor is used to fuse the outputs of the two encoders via cross-attention. We compare GREEN with 7 state-of-the-art TRL methods for 3 downstream tasks, finding that GREEN consistently outperforms all baselines and improves the accuracy of the best-performing baseline by an average of 15.99\%.