Pre-Training General Trajectory Embeddings With Maximum Multi-View Entropy Coding
- 27 December 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 36 (12) , 9037-9050
Abstract
Spatio-temporal trajectories provide valuable information about movement and travel behavior, enabling various downstream tasks that in turn power real-world applications. Learning trajectory embeddings can improve task performance but may incur high computational costs and face limited training data availability. Pre-training learns generic embeddings by means of specially constructed pretext tasks that enable learning from unlabeled data. Existing pre-training methods face (i) difficulties in learning general embeddings due to biases towards certain downstream tasks incurred by the pretext tasks, (ii) limitations in capturing both travel semantics and spatio-temporal correlations, and (iii) the complexity of long, irregularly sampled trajectories. To tackle these challenges, we propose Maximum Multi-view Trajectory Entropy Coding (MMTEC) for learning general and comprehensive trajectory embeddings. We introduce a pretext task that reduces biases in pre-trained trajectory embeddings, yielding embeddings that are useful for a wide variety of downstream tasks. We also propose an attention-based discrete encoder and a NeuralCDE-based continuous encoder that extract and represent travel behavior and continuous spatio-temporal correlations from trajectories in embeddings, respectively. Extensive experiments on two real-world datasets and three downstream tasks offer insight into the design properties of our proposal and indicate that it is capable of outperforming existing trajectory embedding methods.Keywords
All Related Versions
Funding Information
- Fundamental Research Funds for the Central Universities (2021YJS030)
This publication has 33 references indexed in Scilit:
- Trajectory Representation Learning Based on Road Network Partition for Similarity Computation2023
- Deep Fusion for Travel Time Estimation Based on Road Network TopologyIEEE Intelligent Systems, 2022
- Pre-Training Time-Aware Location Embeddings from Spatial-Temporal TrajectoriesIEEE Transactions on Knowledge and Data Engineering, 2021
- Contrastive Multiview Coding2020
- Pre-trained models for natural language processing: A surveyScience China Technological Sciences, 2020
- Online Anomalous Trajectory Detection with Deep Generative Sequence Modeling2020
- DeepMove: Learning Place Representations through Large Scale Movement Data2018
- Deep Representation Learning for Trajectory Similarity Computation2018
- Fast map matching, an algorithm integrating hidden Markov model with precomputationInternational Journal of Geographical Information Science, 2017
- Trajectory clustering via deep representation learning2017