# AdvSGM: Differentially Private Graph Learning via Adversarial Skip-gram Model

arXiv: https://arxiv.org/abs/2503.21426 · HTML: https://mlsanity.com/paper/2503.21426/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 51 references that are in the map.
- First posted on arXiv 27 Mar 2025.

## Builds on (most cited first, 29 of 29)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [node2vec: Scalable Feature Learning for Networks](https://mlsanity.com/paper/1607.00653/) (2016)
- [DeepWalk: Online Learning of Social Representations](https://mlsanity.com/paper/1403.6652/) (2014)
- [LINE: Large-scale Information Network Embedding](https://mlsanity.com/paper/1503.03578/) (2015)
- [Subsampled R'enyi Differential Privacy and Analytical Moments Accountant](https://mlsanity.com/paper/1808.00087/) (2018)
- [Differentially Private Learning Needs Better Features (or Much More Data)](https://mlsanity.com/paper/2011.11660/) (2020)
- [R'enyi Differential Privacy of the Sampled Gaussian Mechanism](https://mlsanity.com/paper/1908.10530/) (2019)
- [Tempered Sigmoid Activations for Deep Learning with Differential Privacy](https://mlsanity.com/paper/2007.14191/) (2020)
- [PTE: Predictive Text Embedding through Large-scale Heterogeneous Text Networks](https://mlsanity.com/paper/1508.00200/) (2015)
- [Differentially Private Model Publishing for Deep Learning](https://mlsanity.com/paper/1904.02200/) (2019)
- [Differentially Private Optimization on Large Model at Small Cost](https://mlsanity.com/paper/2210.00038/) (2022)
- [GAP: Differentially Private Graph Neural Networks with Aggregation Perturbation](https://mlsanity.com/paper/2203.00949/) (2022)
- [Differentially Private Federated Knowledge Graphs Embedding](https://mlsanity.com/paper/2105.07615/) (2021)
- [Node-Level Differentially Private Graph Neural Networks](https://mlsanity.com/paper/2111.15521/) (2021)
- [Releasing Graph Neural Networks with Differential Privacy Guarantees](https://mlsanity.com/paper/2109.08907/) (2021)
- [Improving Deep Learning with Differential Privacy using Gradient Encoding and Denoising](https://mlsanity.com/paper/2007.11524/) (2020)
- [Secure Deep Graph Generation with Link Differential Privacy](https://mlsanity.com/paper/2005.00455/) (2020)
- [Differentially Private Graph Learning via Sensitivity-Bounded Personalized PageRank](https://mlsanity.com/paper/2207.06944/) (2022)
- [ProGAP: Progressive Graph Neural Networks with Differential Privacy Guarantees](https://mlsanity.com/paper/2304.08928/) (2023)
- [Preserving Node-level Privacy in Graph Neural Networks](https://mlsanity.com/paper/2311.06888/) (2023)
- [DPAR: Decoupled Graph Neural Networks with Node-Level Differential Privacy](https://mlsanity.com/paper/2210.04442/) (2022)
- [Stochastic Adaptive Line Search for Differentially Private Optimization](https://mlsanity.com/paper/2008.07978/) (2020)
- [Understanding and Improvement of Adversarial Training for Network Embedding from an Optimization Perspective](https://mlsanity.com/paper/2105.08007/) (2021)
- [FedWalk: Communication Efficient Federated Unsupervised Node Embedding with Differential Privacy](https://mlsanity.com/paper/2205.15896/) (2022)
- [Quantifying Differential Privacy under Temporal Correlations](https://mlsanity.com/paper/1610.07543/) (2016)
- [A Robust and Generalized Framework for Adversarial Graph Embedding](https://mlsanity.com/paper/2105.10651/) (2021)
- [Trajectory Data Collection with Local Differential Privacy](https://mlsanity.com/paper/2307.09339/) (2023)
- [Stateful Switch: Optimized Time Series Release with Local Differential Privacy](https://mlsanity.com/paper/2212.08792/) (2022)

## Built on by (most cited first, 1 of 1)

- [Adversarial Signed Graph Learning with Differential Privacy](https://mlsanity.com/paper/2512.00307/) (2025)

## Abstract (arXiv)

The skip-gram model (SGM), which employs a neural network to generate node vectors, serves as the basis for numerous popular graph embedding techniques. However, since the training datasets contain sensitive linkage information, the parameters of a released SGM may encode private information and pose significant privacy risks. Differential privacy (DP) is a rigorous standard for protecting individual privacy in data analysis. Nevertheless, when applying differential privacy to skip-gram in graphs, it becomes highly challenging due to the complex link relationships, which potentially result in high sensitivity and necessitate substantial noise injection. To tackle this challenge, we present AdvSGM, a differentially private skip-gram for graphs via adversarial training. Our core idea is to leverage adversarial training to privatize skip-gram while improving its utility. Towards this end, we develop a novel adversarial training module by devising two optimizable noise terms that correspond to the parameters of a skip-gram. By fine-tuning the weights between modules within AdvSGM, we can achieve differentially private gradient updates without additional noise injection. Extensive experimental results on six real-world graph datasets show that AdvSGM preserves high data utility across different downstream tasks.