CrossSim: Toward Cross-System Trajectory Similarity Computation via Representation Learning

Trajectory similarity computation is essential for various downstream applications, such as anomaly route detection, order matching, and digital contact tracing. However, its effectiveness is confined within a single system due to privacy concerns associated with sharing raw trajectories across different systems. In this article, we propose CrossSim, a novel framework designed to efficiently retrieve similar trajectories across all systems while preserving individual privacy. Our framework comprises three main components: 1) a Trajectory Encoding Model that transforms trajectories into high-quality representations, where similarity relationships are reflected by their distances; 2) a two-stage optimization mechanism, including a Contrastive Similarity Learning stage and a Federated Similarity Learning stage, that alleviates the impact of heterogeneous similarity relationships across different systems on model training without aggregating raw trajectories; and 3) a Similar Trajectory Retrieval procedure that obtains top-k similar trajectories from all systems without sharing raw trajectories. We conduct comprehensive experiments on three real-world datasets to evaluate the effectiveness of our proposed framework. The evaluation results demonstrate that CrossSim outperforms all existing schemes.