# Privacy-Preserving Graph Embedding based on Local Differential Privacy

arXiv: https://arxiv.org/abs/2310.11060 · HTML: https://mlsanity.com/paper/2310.11060/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 44 references that are in the map.
- First posted on arXiv 17 Oct 2023.

## Builds on (most cited first, 24 of 24)

- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Predict then Propagate: Graph Neural Networks meet Personalized PageRank](https://mlsanity.com/paper/1810.05997/) (2018)
- [Multi-scale Attributed Node Embedding](https://mlsanity.com/paper/1909.13021/) (2019)
- [RAPPOR: Randomized Aggregatable Privacy-Preserving Ordinal Response](https://mlsanity.com/paper/1407.6981/) (2014)
- [Scaling Graph Neural Networks with Approximate PageRank](https://mlsanity.com/paper/2007.01570/) (2020)
- [Minimax Optimal Procedures for Locally Private Estimation](https://mlsanity.com/paper/1604.02390/) (2016)
- [Locally Private Graph Neural Networks](https://mlsanity.com/paper/2006.05535/) (2020)
- [Collecting and Analyzing Multidimensional Data with Local Differential Privacy](https://mlsanity.com/paper/1907.00782/) (2019)
- [NetSMF: Large-Scale Network Embedding as Sparse Matrix Factorization](https://mlsanity.com/paper/1906.11156/) (2019)
- [GAP: Differentially Private Graph Neural Networks with Aggregation Perturbation](https://mlsanity.com/paper/2203.00949/) (2022)
- [Node-Level Differentially Private Graph Neural Networks](https://mlsanity.com/paper/2111.15521/) (2021)
- [Graph Embedding for Recommendation against Attribute Inference Attacks](https://mlsanity.com/paper/2101.12549/) (2021)
- [Pairwise Learning for Neural Link Prediction](https://mlsanity.com/paper/2112.02936/) (2021)
- [Approximate Graph Propagation](https://mlsanity.com/paper/2106.03058/) (2021)
- [Locally Differentially Private Analysis of Graph Statistics](https://mlsanity.com/paper/2010.08688/) (2020)
- [Estimating Numerical Distributions under Local Differential Privacy](https://mlsanity.com/paper/1912.01051/) (2019)
- [Towards Private Learning on Decentralized Graphs with Local Differential Privacy](https://mlsanity.com/paper/2201.09398/) (2022)
- [Scalable Graph Embeddings via Sparse Transpose Proximities](https://mlsanity.com/paper/1905.07245/) (2019)
- [LPGNet: Link Private Graph Networks for Node Classification](https://mlsanity.com/paper/2205.03105/) (2022)
- [Differentially Private Graph Learning via Sensitivity-Bounded Personalized PageRank](https://mlsanity.com/paper/2207.06944/) (2022)
- [Differentially Private Densest Subgraph Detection](https://mlsanity.com/paper/2105.13287/) (2021)
- [Gromov-Wasserstein Discrepancy with Local Differential Privacy for Distributed Structural Graphs](https://mlsanity.com/paper/2202.00808/) (2022)
- [Differential Privacy from Locally Adjustable Graph Algorithms: k-Core Decomposition, Low Out-Degree Ordering, and Densest Subgraphs](https://mlsanity.com/paper/2211.10887/) (2022)
- [Learning Based Proximity Matrix Factorization for Node Embedding](https://mlsanity.com/paper/2106.05476/) (2021)

## Built on by (most cited first, 3 of 3)

- [Toward General and Robust LLM-enhanced Text-attributed Graph Learning](https://mlsanity.com/paper/2504.02343/) (2025)
- [Devil's Hand: Data Poisoning Attacks to Locally Private Graph Learning Protocols](https://mlsanity.com/paper/2506.09803/) (2025)
- [Trust-But-Verify: Poisoning-Resilient Locally Private Graph Learning Protocols](https://mlsanity.com/paper/2609.07063/) (2026)

## Abstract (arXiv)

Graph embedding has become a powerful tool for learning latent representations of nodes in a graph. Despite its superior performance in various graph-based machine learning tasks, serious privacy concerns arise when the graph data contains personal or sensitive information. To address this issue, we investigate and develop graph embedding algorithms that satisfy local differential privacy (LDP). We introduce a novel privacy-preserving graph embedding framework, named PrivGE, to protect node data privacy. Specifically, we propose an LDP mechanism to obfuscate node data and utilize personalized PageRank as the proximity measure to learn node representations. Furthermore, we provide a theoretical analysis of the privacy guarantees and utility offered by the PrivGE framework. Extensive experiments on several real-world graph datasets demonstrate that PrivGE achieves an optimal balance between privacy and utility, and significantly outperforms existing methods in node classification and link prediction tasks.