发表机构
Aalborg University; University of Electronic Science and Technology of China（奥尔堡大学; 电子科技大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对现有轨迹相似度学习方法的缺陷，提出LB-TrajRep下界表示框架，通过数据驱动枢轴选择策略优化下界紧密度，在多轨迹距离度量下显著优于当前最优神经嵌入方法。
AI 中文摘要
轨迹相似度学习是复杂距离度量下高效轨迹检索的基础。现有基于学习的方法通常依赖训练以近似轨迹距离或排序的嵌入，但往往缺乏对原始距离的保证，在不同距离度量上性能不稳定，且训练成本高。我们从下界表示视角重新研究轨迹相似度学习，提出LB-TrajRep，一种不依赖深度神经嵌入的统一下界表示框架。该框架从一组下界分量构造单向量表示，可为动态时间规整（DTW）、豪斯多夫距离、离散弗雷歇距离（DFD）等多种经典轨迹距离提供可容许且可解释的下界。在该框架内，我们实例化点-枢轴分量，其天然支持度量与非度量距离，且兼容标准基于向量的检索流水线。为提升排序质量，我们开发两种数据驱动的枢轴选择策略，分别显式优化下界紧密度、优先处理困难近邻轨迹对。在真实轨迹数据集上的大量实验表明，所提出的下界表示在不同距离度量下均能持续优于当前最优的神经轨迹嵌入，在豪斯多夫距离和DFD上的top-k排序准确率提升最高达20%--60%，在DTW上提升15%--40%。
英文摘要
Trajectory similarity learning is fundamental to efficient trajectory retrieval under complex distance measures. Existing learning-based methods typically rely on embeddings trained to approximate trajectory distances or rankings, but they often lack guarantees with respect to the original distances, exhibit unstable performance across distance measures, and incur substantial training costs. We revisit trajectory similarity learning from a lower-bound representation perspective and propose LB-TrajRep, a unified lower-bound representation framework independent of deep neural embeddings. This framework constructs single-vector representations from a set of lower-bound components, enabling admissible and interpretable lower bounds for multiple classical trajectory distances, including Dynamic Time Warping (DTW), Hausdorff distance, and Discrete Fréchet Distance (DFD). Within this framework, we instantiate point-pivot components, which naturally support both metric and non-metric distances and remain compatible with standard vector-based retrieval pipelines. To improve ranking quality, we develop two data-driven pivot selection strategies that explicitly optimize lower-bound tightness and prioritize hard near-neighbor trajectory pairs, respectively. Extensive experiments on real-world trajectory datasets show that the proposed lower-bound representations are able to consistently outperform state-of-the-art neural trajectory embeddings across diverse distance measures, improving top-$k$ ranking accuracy by up to 20\%--60\% on the Hausdorff distance and DFD and by 15\%--40\% on DTW.
Comments15 pages, 5 figures, accepted version and accepted by PVLDBv19
