# GeoPointGAN: Synthetic Spatial Data with Local Label Differential Privacy

arXiv: https://arxiv.org/abs/2205.08886 · HTML: https://mlsanity.com/paper/2205.08886/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 81 references that are in the map.
- First posted on arXiv 18 May 2022.

## Builds on (most cited first, 30 of 35)

- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [Differentially Private Generative Adversarial Network](https://mlsanity.com/paper/1802.06739/) (2018)
- [3D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutions](https://mlsanity.com/paper/1905.06292/) (2019)
- [PU-GAN: a Point Cloud Upsampling Adversarial Network](https://mlsanity.com/paper/1907.10844/) (2019)
- [SELF: Learning to Filter Noisy Labels with Self-Ensembling](https://mlsanity.com/paper/1910.01842/) (2019)
- [DP-CGAN: Differentially Private Synthetic Data and Label Generation](https://mlsanity.com/paper/2001.09700/) (2020)
- [Deep Learning with Label Differential Privacy](https://mlsanity.com/paper/2102.06062/) (2021)
- [Generative Models for Effective ML on Private, Decentralized Datasets](https://mlsanity.com/paper/1911.06679/) (2019)
- [Point Cloud GAN](https://mlsanity.com/paper/1810.05795/) (2018)
- [Deep Generative Modeling of LiDAR Data](https://mlsanity.com/paper/1812.01180/) (2018)
- [RL-GAN-Net: A Reinforcement Learning Agent Controlled GAN Network for Real-Time Point Cloud Shape Completion](https://mlsanity.com/paper/1904.12304/) (2019)
- [LG-GAN: Label Guided Adversarial Network for Flexible Targeted Attack of Point Cloud-based Deep Networks](https://mlsanity.com/paper/2011.00566/) (2020)
- [Deceive D: Adaptive Pseudo Augmentation for GAN Training with Limited Data](https://mlsanity.com/paper/2111.06849/) (2021)
- [Differentially Private Synthetic Medical Data Generation using Convolutional GANs](https://mlsanity.com/paper/2012.11774/) (2020)
- [Antipodes of Label Differential Privacy: PATE and ALIBI](https://mlsanity.com/paper/2106.03408/) (2021)
- [Wasserstein Learning of Deep Generative Point Process Models](https://mlsanity.com/paper/1705.08051/) (2017)
- [DisturbLabel: Regularizing CNN on the Loss Layer](https://mlsanity.com/paper/1605.00055/) (2016)
- [Differentially Private Generative Adversarial Networks for Time Series, Continuous, and Discrete Open Data](https://mlsanity.com/paper/1901.02477/) (2019)
- [Adversarial Text Generation via Feature-Mover's Distance](https://mlsanity.com/paper/1809.06297/) (2018)
- [Kamino: Constraint-Aware Differentially Private Data Synthesis](https://mlsanity.com/paper/2012.15713/) (2020)
- [Label differential privacy via clustering](https://mlsanity.com/paper/2110.02159/) (2021)
- [Protecting Locations with Differential Privacy under Temporal Correlations](https://mlsanity.com/paper/1410.5919/) (2014)
- [MRGAN: Multi-Rooted 3D Shape Generation with Unsupervised Part Disentanglement](https://mlsanity.com/paper/2007.12944/) (2020)
- [SPATE-GAN: Improved Generative Modeling of Dynamic Spatio-Temporal Patterns with an Autoregressive Embedding Loss](https://mlsanity.com/paper/2109.15044/) (2021)
- [A Progressive Conditional Generative Adversarial Network for Generating Dense and Colored 3D Point Clouds](https://mlsanity.com/paper/2010.05391/) (2020)
- [Auxiliary-task learning for geographic data with autoregressive embeddings](https://mlsanity.com/paper/2006.10461/) (2020)

## Built on by (most cited first, 9 of 9)

- [Machine Learning for Synthetic Data Generation: A Review](https://mlsanity.com/paper/2302.04062/) (2023)
- [SoK: Can Trajectory Generation Combine Privacy and Utility?](https://mlsanity.com/paper/2403.07218/) (2024)
- [Exactly Minimax-Optimal Locally Differentially Private Sampling](https://mlsanity.com/paper/2410.22699/) (2024)
- [Locally Private Estimation with Public Features](https://mlsanity.com/paper/2405.13481/) (2024)
- [Enhancing Learning with Label Differential Privacy by Vector Approximation](https://mlsanity.com/paper/2405.15150/) (2024)
- [Locally Optimal Private Sampling: Beyond the Global Minimax](https://mlsanity.com/paper/2510.09485/) (2025)
- [Synthetic Trajectory Generation Through Convolutional Neural Networks](https://mlsanity.com/paper/2407.16938/) (2024)
- [Differentially private synthesis of Spatial Point Processes](https://mlsanity.com/paper/2502.18198/) (2025)
- [What is the Cost of Differential Privacy for Deep Learning-Based Trajectory Generation?](https://mlsanity.com/paper/2506.09312/) (2025)

## Abstract (arXiv)

Synthetic data generation is a fundamental task for many data management and data science applications. Spatial data is of particular interest, and its sensitive nature often leads to privacy concerns. We introduce GeoPointGAN, a novel GAN-based solution for generating synthetic spatial point datasets with high utility and strong individual level privacy guarantees. GeoPointGAN's architecture includes a novel point transformation generator that learns to project randomly generated point co-ordinates into meaningful synthetic co-ordinates that capture both microscopic (e.g., junctions, squares) and macroscopic (e.g., parks, lakes) geographic features. We provide our privacy guarantees through label local differential privacy, which is more practical than traditional local differential privacy. We seamlessly integrate this level of privacy into GeoPointGAN by augmenting the discriminator to the point level and implementing a randomized response-based mechanism that flips the labels associated with the 'real' and 'fake' points used in training. Extensive experiments show that GeoPointGAN significantly outperforms recent solutions, improving by up to 10 times compared to the most competitive baseline. We also evaluate GeoPointGAN using range, hotspot, and facility location queries, which confirm the practical effectiveness of GeoPointGAN for privacy-preserving querying. The results illustrate that a strong level of privacy is achieved with little-to-no adverse utility cost, which we explain through the generalization and regularization effects that are realized by flipping the labels of the data during training.