Jointly Contrastive Representation Learning on Road Network and Trajectory

TL;DR

This paper introduces a unified contrastive learning framework that jointly learns representations of road networks and trajectories, capturing inter-scale relations to improve downstream traffic prediction tasks.

Contribution

It proposes a novel end-to-end contrastive learning method with domain-specific augmentations and cross-scale contrast, effectively bridging road network and trajectory representations.

Findings

Enhanced performance on real-world datasets

Effective cross-scale representation learning

Improved results in downstream traffic tasks

Abstract

Road network and trajectory representation learning are essential for traffic systems since the learned representation can be directly used in various downstream tasks (e.g., traffic speed inference, and travel time estimation). However, most existing methods only contrast within the same scale, i.e., treating road network and trajectory separately, which ignores valuable inter-relations. In this paper, we aim to propose a unified framework that jointly learns the road network and trajectory representations end-to-end. We design domain-specific augmentations for road-road contrast and trajectory-trajectory contrast separately, i.e., road segment with its contextual neighbors and trajectory with its detour replaced and dropped alternatives, respectively. On top of that, we further introduce the road-trajectory cross-scale contrast to bridge the two scales by maximizing the total mutual information. Unlike the existing cross-scale contrastive learning methods on graphs that only contrast a graph and its belonging nodes, the contrast between road segment and trajectory is elaborately tailored via novel positive sampling and adaptive weighting strategies. We conduct prudent experiments based on two real-world datasets with four downstream tasks, demonstrating improved performance and effectiveness. The code is available at https://github.com/mzy94/JCLRNT.