Semantic-Enhanced Representation Learning for Road Networks With Temporal Dynamics

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: Semantic-Enhanced Representation Learning for Road Networks With Temporal Dynamics
Συγγραφείς: Yile Chen, Xiucheng Li, Gao Cong, Zhifeng Bao, Cheng Long
Πηγή: IEEE Transactions on Mobile Computing. 24:9413-9427
Publication Status: Preprint
Στοιχεία εκδότη: Institute of Electrical and Electronics Engineers (IEEE), 2025.
Έτος έκδοσης: 2025
Θεματικοί όροι: FOS: Computer and information sciences, Computer Science - Machine Learning, Artificial Intelligence (cs.AI), Computer Science - Artificial Intelligence, Machine Learning (cs.LG)
Περιγραφή: In this study, we introduce a novel framework called Toast for learning general-purpose representations of road networks, along with its advanced counterpart DyToast, designed to enhance the integration of temporal dynamics to boost the performance of various time-sensitive downstream tasks. Specifically, we propose to encode two pivotal semantic characteristics intrinsic to road networks: traffic patterns and traveling semantics. To achieve this, we refine the skip-gram module by incorporating auxiliary objectives aimed at predicting the traffic context associated with a target road segment. Moreover, we leverage trajectory data and design pre-training strategies based on Transformer to distill traveling semantics on road networks. DyToast further augments this framework by employing unified trigonometric functions characterized by their beneficial properties, enabling the capture of temporal evolution and dynamic nature of road networks more effectively. With these proposed techniques, we can obtain representations that encode multi-faceted aspects of knowledge within road networks, applicable across both road segment-based applications and trajectory-based applications. Extensive experiments on two real-world datasets across three tasks demonstrate that our proposed framework consistently outperforms the state-of-the-art baselines by a significant margin.
Τύπος εγγράφου: Article
ISSN: 2161-9875
1536-1233
DOI: 10.1109/tmc.2025.3562656
DOI: 10.48550/arxiv.2403.11495
Σύνδεσμος πρόσβασης: http://arxiv.org/abs/2403.11495
Rights: IEEE Copyright
arXiv Non-Exclusive Distribution
Αριθμός Καταχώρησης: edsair.doi.dedup.....2004a94c986cf659e66a75d77a947556
Βάση Δεδομένων: OpenAIRE
Περιγραφή
ISSN:21619875
15361233
DOI:10.1109/tmc.2025.3562656