DBScholar

Back to papers

SimRN: Trajectory Similarity Learning in Road Networks based on Distributed Deep Reinforcement Learning

Summary: SimRN, the first DRL-based trajectory-similarity framework for road networks, integrates spatio-temporal prompt extraction, DRL-based trajectory representation with automatic parameter selection and parallel training, plus graph contrastive learning. Yields 20–40% accuracy gains, 2–4× speedups, and strong generalization on tiny training sets via self-supervised contrastive sampling that preserves spatial and temporal constraints. (summarized by gpt-5-mini on Feb 09 2026)

Paper ID
14047
Venue
VLDB
Year
2025
Pagerank
5.093636e-05
Overall Rank
10,849 | 25.57%
DOI
10.14778/3734839.3734844

Incoming Non-self Citations Over Time

No non-self incoming citations found for this paper in this database.

Authors

BibTeX Citation

@article{hu_vldb25,
        title = {{SimRN: Trajectory Similarity Learning in Road Networks based on Distributed Deep Reinforcement Learning}},
        author = {Hu, Danlei and Li, Yilin and Chen, Lu and Fang, Ziquan and Li, Yushuai and Gao, Yunjun and Li, Tianyi},
        journal = {PVLDB},
        series = {{VLDB} '25},
        volume = {18},
        number = {7},
        pages = {2057--2069},
        doi = {10.14778/3734839.3734844},
        url = {https://doi.org/10.14778/3734839.3734844},
        year = {2025}
}

Incoming Citations (Sorted by Pagerank)

Showing 0 of 0 citing papers.

Rank Citing Paper Year Venue Pagerank
Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 10 of 10 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Previous Page 1 / 1 Next

Semantically Similar Papers