A Neural Approach to Spatio-Temporal Data Release with User-Level Differential Privacy

Summary: Neural approach uses a variational auto-encoder to sanitize spatio-temporal data under user-level DP, reducing DP noise without sacrificing utility. Extensive experiments on real data show superior accuracy and privacy tradeoffs versus benchmarks and high-budget releases. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID: 6586
Venue: SIGMOD
Year: 2023
Pagerank: 5.5711643e-05
Overall Rank: 7,668 | 47.40%
DOI: 10.1145/3588701

Incoming Non-self Citations Over Time

Authors

1. Ritesh Ahuja (University of Southern California)
2. Sepanta Zeighami (University of Southern California)
3. Gabriel Ghinita (Hamad Bin Khalifa University)
4. Cyrus Shahabi (University of Southern California)

BibTeX Citation

@inproceedings{ahuja_sigmod23,
        title = {{A Neural Approach to Spatio-Temporal Data Release with User-Level Differential Privacy}},
        author = {Ahuja, Ritesh and Zeighami, Sepanta and Ghinita, Gabriel and Shahabi, Cyrus},
        series = {{SIGMOD} '23},
        booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
        publisher = {Association for Computing Machinery},
        doi = {10.1145/3588701},
        url = {https://dl.acm.org/doi/10.1145/3588701},
        year = {2023}
}

Incoming Citations (Sorted by Pagerank)

Showing 3 of 3 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
9,101	NeuroSketch: Fast and Approximate Evaluation of Range Aggregate Queries with Neural Networks	2023	SIGMOD	5.324758e-05
10,677	RLER-TTE: An Efficient and Effective Framework for En Route Travel Time Estimation with Reinforcement Learning	2025	SIGMOD	5.093636e-05
10,914	Calibrating Noise for Group Privacy in Subsampled Mechanisms	2025	VLDB	5.093636e-05

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
121	Boosting the Accuracy of Differentially Private Histograms Through Consistency	2010	VLDB	0.00031639377
1,308	PrivTree: A Differentially Private Algorithm for Hierarchical Decompositions	2016	SIGMOD	0.00011216361
1,504	A Data- and Workload-Aware Algorithm for Range Queries Under Differential Privacy	2014	VLDB	0.00010548904
2,167	Optimizing error of high-dimensional statistical queries under differential privacy	2018	VLDB	9.047803e-05
2,300	Principled Evaluation of Differentially Private Algorithms using DPBench	2016	SIGMOD	8.7833594e-05
4,185	Bolt-on Differential Privacy for Scalable Stochastic Gradient Descent-based Analytics	2017	SIGMOD	6.8462927e-05
4,361	ϵktelo: A Framework for Defining Differentially-Private Computations	2018	SIGMOD	6.7443476e-05
5,555	Practical Differential Privacy via Grouping and Smoothing	2013	VLDB	6.1774651e-05
6,804	A Neural Database for Differentially Private Spatial Range Queries	2022	VLDB	5.768025e-05
13,451	Estimating Spread of Contact-Based Contagions in a Population Through Sub-Sampling	2021	VLDB	-

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	8,908	Privacy and Accuracy-Aware AI/ML Model Deduplication	2025	SIGMOD
2	8,198	Local Dampening: Differential Privacy for Non-numeric Queries via Local Sensitivity	2021	VLDB
3	6,083	Global and Local Differentially Private Release of Count-Weighted Graphs	2023	SIGMOD
4	10,335	A General Framework for Per-record Differential Privacy	2026	SIGMOD
5	7,841	Quantifying identifiability to choose and audit epsilon in differentially private deep learning	2021	VLDB
6	11,259	HRNet: Differentially Private Hierarchical and Multi-Resolution Network for Human Mobility Data Synthesization	2024	VLDB
7	2,780	A Framework for Protecting Worker Location Privacy in Spatial Crowdsourcing	2014	VLDB
8	5,327	Real-World Trajectory Sharing with Local Differential Privacy	2021	VLDB
9	6,579	A Deep Generative Model for Trajectory Modeling and Utilization	2023	VLDB
10	6,804	A Neural Database for Differentially Private Spatial Range Queries	2022	VLDB