Quantifying Point Contributions: A Lightweight Framework for Efficient and Effective Query-Driven Trajectory Simplification
Summary: MLSimp jointly uses attention-based GNNs to score trajectory-point globality and local uniqueness without iterative deletion, and diffusion models to preserve salient points under aggressive compression. It cuts simplification time 42–70% and improves query accuracy up to 34.6%. (summarized by gpt-5.6-luna on Jul 24 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Yumeng Song (Northeastern University)
- 2. Yu Gu (Northeastern University)
- 3. Tianyi Li (Aalborg University)
- 4. Yushuai Li (Aalborg University)
- 5. Christian S. Jensen (Aalborg University)
- 6. Ge Yu (Northeastern University)
BibTeX Citation
@article{song_vldb25,
title = {{Quantifying Point Contributions: A Lightweight Framework for Efficient and Effective Query-Driven Trajectory Simplification}},
author = {Song, Yumeng and Gu, Yu and Li, Tianyi and Li, Yushuai and Jensen, Christian S. and Yu, Ge},
journal = {PVLDB},
series = {{VLDB} '25},
volume = {18},
number = {2},
pages = {453--465},
doi = {10.14778/3705829.3705858},
url = {https://doi.org/10.14778/3705829.3705858},
year = {2025}
}Incoming Citations (Sorted by Pagerank)
Showing 2 of 2 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 10,438 | DimWeaver: Dimensional Weaved Trajectory Compression | 2026 | SIGMOD | 4.9793485e-05 |
| 10,743 | MH-GIN: Multi-scale Heterogeneous Graph-based Imputation Network for AIS Data | 2026 | VLDB | 4.9793485e-05 |
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.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 227 | Robust and Fast Similarity Search for Moving Object Trajectories | 2005 | SIGMOD | 0.0002393284 |
| 917 | Trajectory Clustering: A Partition-and-Group Framework | 2007 | SIGMOD | 0.00013091246 |
| 2,501 | Trajectory Simplification: On Minimizing the Direction-based Error | 2015 | VLDB | 8.3808899e-05 |
| 2,914 | Direction-Preserving Trajectory Simplification | 2013 | VLDB | 7.8619624e-05 |
| 3,009 | Trajectory Simplification: An Experimental Study and Quality Analysis | 2018 | VLDB | 7.7578378e-05 |
| 4,468 | Real-time Workload Pattern Analysis for Large-scale Cloud Databases | 2023 | VLDB | 6.5863349e-05 |
| 4,534 | SimpleTS: An Efficient and Universal Model Selection Framework for Time Series Forecasting | 2023 | VLDB | 6.5561421e-05 |
| 6,130 | Compression of Uncertain Trajectories in Road Networks | 2020 | VLDB | 5.8783975e-05 |
| 6,730 | Trajectory Similarity Measurement: An Efficiency Perspective | 2024 | VLDB | 5.6939772e-05 |
| 7,975 | TRACE: Real-time Compression of Streaming Trajectories in Road Networks | 2021 | VLDB | 5.41472e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 11,265 | GraphSparseNet: a Novel Method for Large Scale Traffic Flow Prediction | 2025 | VLDB |
| 2 | 2,914 | Direction-Preserving Trajectory Simplification | 2013 | VLDB |
| 3 | 2,501 | Trajectory Simplification: On Minimizing the Direction-based Error | 2015 | VLDB |
| 4 | 6,730 | Trajectory Similarity Measurement: An Efficiency Perspective | 2024 | VLDB |
| 5 | 11,255 | SimRN: Trajectory Similarity Learning in Road Networks based on Distributed Deep Reinforcement Learning | 2025 | VLDB |
| 6 | 11,340 | SIMformer: Single-Layer Vanilla Transformer Can Learn Free-Space Trajectory Similarity | 2025 | VLDB |
| 7 | 11,214 | Revisiting CNNs for Trajectory Similarity Learning | 2025 | VLDB |
| 8 | 3,770 | Calibrating Trajectory Data for Similarity-based Analysis | 2013 | SIGMOD |
| 9 | 6,130 | Compression of Uncertain Trajectories in Road Networks | 2020 | VLDB |
| 10 | 3,009 | Trajectory Simplification: An Experimental Study and Quality Analysis | 2018 | VLDB |