K Nearest Neighbor-Guided Trajectory Similarity Learning

2025-02-01

AI Summary

To address low measurement accuracy, difficulty in modeling fine-grained patterns, and insufficient exploitation of training signals in trajectory similarity computation, this paper proposes TSMini. Methodologically, it introduces a novel sub-view multi-granularity modeling mechanism that hierarchically decomposes features to jointly capture local and global trajectory structures. Additionally, it designs a k-nearest-neighbor-guided, ranking-aware contrastive loss to jointly optimize absolute similarity estimation and relative ordinal relationships. The framework unifies geometric, semantic, and topological trajectory characteristics without relying on handcrafted distance functions. Evaluated across multiple standard trajectory similarity tasks—including retrieval, clustering, and matching—TSMini achieves an average 22% improvement in accuracy over state-of-the-art methods, demonstrating superior generalizability and robustness.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Machine Learning: Multi-instance/Multi-view Learning
• Computer Vision: Motion & Tracking

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Trajectory similarity is fundamental to many spatio-temporal data mining applications. Recent studies propose deep learning models to approximate conventional trajectory similarity measures, exploiting their fast inference time once trained. Although efficient inference has been reported, challenges remain in similarity approximation accuracy due to difficulties in trajectory granularity modeling and in exploiting similarity signals in the training data. To fill this gap, we propose TSMini, a highly effective trajectory similarity model with a sub-view modeling mechanism capable of learning multi-granularity trajectory patterns and a k nearest neighbor-based loss that guides TSMini to learn not only absolute similarity values between trajectories but also their relative similarity ranks. Together, these two innovations enable highly accurate trajectory similarity approximation. Experiments show that TSMini can outperform the state-of-the-art models by 22% in accuracy on average when learning trajectory similarity measures.

Problem

• Trajectory Similarity Estimation
• Temporal-Spatial Data Analysis
• Modeling Complexity

Innovation

• TSMini model
• neighbor-based loss function
• trajectory similarity estimation