TMLKD: Few-shot Trajectory Metric Learning via Knowledge Distillation
Summary: TMLKD: a knowledge-distillation framework for few-shot trajectory metric learning that tackles domain shift by adversarially separating domain-invariant from domain-specific features to transfer robust representations. Enriches sparse target labels via teachers' list-wise rank knowledge with adaptive reliability weighting to avoid misleading supervision; empirically outperforms baselines on three real datasets. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
No non-self incoming citations found for this paper in this database.
Authors
- 1. Danling Lai (Soochow University)
- 2. Jiajie Xu (Soochow University)
- 3. Jianfeng Qu (Soochow University)
- 4. Pingfu Chao (Soochow University)
- 5. Junhua Fang (Soochow University)
- 6. Chengfei Liu (Swinburne University of Technology)
BibTeX Citation
@article{lai_vldb25,
title = {{TMLKD: Few-shot Trajectory Metric Learning via Knowledge Distillation}},
author = {Lai, Danling and Xu, Jiajie and Qu, Jianfeng and Chao, Pingfu and Fang, Junhua and Liu, Chengfei},
journal = {PVLDB},
series = {{VLDB} '25},
volume = {18},
number = {8},
pages = {2308--2320},
doi = {10.14778/3742728.3742729},
url = {https://doi.org/10.14778/3742728.3742729},
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 3 of 3 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 221 | Robust and Fast Similarity Search for Moving Object Trajectories | 2005 | SIGMOD | 0.00024224879 |
| 303 | On The Marriage of Lp-norms and Edit Distance | 2004 | VLDB | 0.00021956234 |
| 3,267 | FTW: Fast Similarity Search under the Time Warping Distance | 2005 | PODS | 7.5816553e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 5,112 | Fast Large-Scale Trajectory Clustering | 2020 | VLDB |
| 2 | 11,295 | TERI: An Effective Framework for Trajectory Recovery with Irregular Time Intervals | 2024 | VLDB |
| 3 | 2,656 | TraClass: Trajectory Classification Using Hierarchical Region-Based and Trajectory-Based Clustering | 2008 | VLDB |
| 4 | 6,579 | A Deep Generative Model for Trajectory Modeling and Utilization | 2023 | VLDB |
| 5 | 7,669 | Multi-Modal Transportation Recommendation with Unified Route Representation Learning | 2021 | VLDB |
| 6 | 10,953 | SIMformer: Single-Layer Vanilla Transformer Can Learn Free-Space Trajectory Similarity | 2025 | VLDB |
| 7 | 10,801 | Revisiting CNNs for Trajectory Similarity Learning | 2025 | VLDB |
| 8 | 3,365 | Spatial and Temporal Constrained Ranked Retrieval over Videos | 2022 | VLDB |
| 9 | 11,100 | RED: Effective Trajectory Representation Learning with Comprehensive Information | 2025 | VLDB |
| 10 | 6,953 | Trajectory Similarity Measurement: An Efficiency Perspective | 2024 | VLDB |