HRNet: Differentially Private Hierarchical and Multi-Resolution Network for Human Mobility Data Synthesization
Summary: HRNet: a differentially private deep generative model for human mobility that combines hierarchical location encoding, multi-resolution multi-task learning, and private pre-training to address sparsity and high-dimensional trajectories. Empirical results on real-world data show substantially improved utility–privacy trade-offs versus prior DP synthesis methods. (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. Shun Takagi
- 2. Li Xiong
- 3. Fumiyuki Kato
- 4. Yang Cao
- 5. Masatoshi Yoshikawa
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 4 of 4 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 453 | Towards Practical Differential Privacy for SQL Queries | 2018 | VLDB | 0.00022741848 |
| 1,520 | PrivTree: A Differentially Private Algorithm for Hierarchical Decompositions | 2016 | SIGMOD | 0.00011535148 |
| 3,907 | DPT: Differentially Private Trajectory Synthesis Using Hierarchical Reference Systems | 2015 | VLDB | 6.6395929e-05 |
| 6,425 | A Deep Generative Model for Trajectory Modeling and Utilization | 2023 | VLDB | 5.0670573e-05 |
Previous
Page 1 / 1
Next