Towards Robust Trajectory Embedding For Similarity Computation: When Triangle Inequality Violations In Distance Metrics Matter

Abstract

Trajectory similarity is a cornerstone of trajectory data management and analysis. Traditional similarity functions often suffer from high computational complexity and a reliance on specific distance metrics, prompting a shift towards deep representation learning in Euclidean space. However, existing Euclidean-based trajectory embeddings often face challenges due to the triangle inequality constraints that do not universally hold for trajectory data. To address this issue, this paper introduces a novel approach by incorporating non-Euclidean geometry, specifically hyperbolic space, into trajectory representation learning. We present the first-ever integration of hyperbolic space to resolve the inherent limitations of the triangle inequality in Euclidean embeddings. In particular, we achieve it by designing a Lorentz distance measure, which is proven to overcome triangle inequality constraints. Additionally, we design a model-agnostic framework LH-plugin to seamlessly integrate hyperbol

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keysi2025towards

Related papers

• Simple Distances For Trajectories Via Landmarks (2018)4.52
• Contrast & Compress: Learning Lightweight Embeddings For Short Trajectories (2025)0.00
• Geopth: A Lightweight Approach To Category-based Trajectory Retrieval Via Geometric Prototype Trajectory Hashing (2025)0.00
• Exact Trajectory Similarity Search With N-tree: An Efficient Metric Index For Knn And Range Queries (2024)0.00
• Human Motion Analysis With Deep Metric Learning (2018)11.58
• A TRIANGLE Enables Multimodal Alignment Beyond Cosine Similarity (2025)0.00
• Hyperbolic Image Embeddings (2019)17.91
• A Practical Index Structure Supporting Fr\'echet Proximity Queries Among Trajectories (2020)6.34