# ST-DPGAN: A Privacy-preserving Framework for Spatiotemporal Data Generation

arXiv: https://arxiv.org/abs/2406.03404 · HTML: https://mlsanity.com/paper/2406.03404/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 60 references that are in the map.
- First posted on arXiv 4 Jun 2024.

## Builds on (most cited first, 20 of 20)

- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Fast Graph Representation Learning with PyTorch Geometric](https://mlsanity.com/paper/1903.02428/) (2019)
- [Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting](https://mlsanity.com/paper/1709.04875/) (2017)
- [Graph WaveNet for Deep Spatial-Temporal Graph Modeling](https://mlsanity.com/paper/1906.00121/) (2019)
- [Self-Attention Generative Adversarial Networks](https://mlsanity.com/paper/1805.08318/) (2018)
- [Wasserstein GAN](https://mlsanity.com/paper/1701.07875/) (2017)
- [Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data](https://mlsanity.com/paper/1610.05755/) (2016)
- [Differentially Private Generative Adversarial Network](https://mlsanity.com/paper/1802.06739/) (2018)
- [Differentially Private Diffusion Models](https://mlsanity.com/paper/2210.09929/) (2022)
- [Differential Privacy Dynamics of Langevin Diffusion and Noisy Gradient Descent](https://mlsanity.com/paper/2102.05855/) (2021)
- [MobTCast: Leveraging Auxiliary Trajectory Forecasting for Human Mobility Prediction](https://mlsanity.com/paper/2110.01401/) (2021)
- [Generative Adversarial Networks for Spatio-temporal Data: A Survey](https://mlsanity.com/paper/2008.08903/) (2020)
- [Differentially Private Data Generative Models](https://mlsanity.com/paper/1812.02274/) (2018)
- [Multimodal Pretraining, Adaptation, and Generation for Recommendation: A Survey](https://mlsanity.com/paper/2404.00621/) (2024)
- [Privacy in Social Media: Identification, Mitigation and Applications](https://mlsanity.com/paper/1808.02191/) (2018)
- [PMG : Personalized Multimodal Generation with Large Language Models](https://mlsanity.com/paper/2404.08677/) (2024)
- [Voice-Indistinguishability: Protecting Voiceprint in Privacy-Preserving Speech Data Release](https://mlsanity.com/paper/2004.07442/) (2020)
- [TERMCast: Temporal Relation Modeling for Effective Urban Flow Forecasting](https://mlsanity.com/paper/2011.05554/) (2020)
- [FADACS: A Few-shot Adversarial Domain Adaptation Architecture for Context-Aware Parking Availability Sensing](https://mlsanity.com/paper/2007.08551/) (2020)

## Abstract (arXiv)

Spatiotemporal data is prevalent in a wide range of edge devices, such as those used in personal communication and financial transactions. Recent advancements have sparked a growing interest in integrating spatiotemporal analysis with large-scale language models. However, spatiotemporal data often contains sensitive information, making it unsuitable for open third-party access. To address this challenge, we propose a Graph-GAN-based model for generating privacy-protected spatiotemporal data. Our approach incorporates spatial and temporal attention blocks in the discriminator and a spatiotemporal deconvolution structure in the generator. These enhancements enable efficient training under Gaussian noise to achieve differential privacy. Extensive experiments conducted on three real-world spatiotemporal datasets validate the efficacy of our model. Our method provides a privacy guarantee while maintaining the data utility. The prediction model trained on our generated data maintains a competitive performance compared to the model trained on the original data.