# Towards Private Learning on Decentralized Graphs with Local Differential Privacy

arXiv: https://arxiv.org/abs/2201.09398 · HTML: https://mlsanity.com/paper/2201.09398/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 45 references that are in the map.
- First posted on arXiv 23 Jan 2022.

## Builds on (most cited first, 22 of 22)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Self-Normalizing Neural Networks](https://mlsanity.com/paper/1706.02515/) (2017)
- [Modeling polypharmacy side effects with graph convolutional networks](https://mlsanity.com/paper/1802.00543/) (2018)
- [Differentially Private Learning Needs Better Features (or Much More Data)](https://mlsanity.com/paper/2011.11660/) (2020)
- [Identity-aware Graph Neural Networks](https://mlsanity.com/paper/2101.10320/) (2021)
- [Collecting Telemetry Data Privately](https://mlsanity.com/paper/1712.01524/) (2017)
- [Predicting multicellular function through multi-layer tissue networks](https://mlsanity.com/paper/1707.04638/) (2017)
- [Characteristic Functions on Graphs: Birds of a Feather, from Statistical Descriptors to Parametric Models](https://mlsanity.com/paper/2005.07959/) (2020)
- [Stealing Links from Graph Neural Networks](https://mlsanity.com/paper/2005.02131/) (2020)
- [Regularization for Deep Learning: A Taxonomy](https://mlsanity.com/paper/1710.10686/) (2017)
- [Quantifying Privacy Leakage in Graph Embedding](https://mlsanity.com/paper/2010.00906/) (2020)
- [Membership Inference Attack on Graph Neural Networks](https://mlsanity.com/paper/2101.06570/) (2021)
- [Cross-Node Federated Graph Neural Network for Spatio-Temporal Data Modeling](https://mlsanity.com/paper/2106.05223/) (2021)
- [LinkTeller: Recovering Private Edges from Graph Neural Networks via Influence Analysis](https://mlsanity.com/paper/2108.06504/) (2021)
- [Locally Private Graph Neural Networks](https://mlsanity.com/paper/2006.05535/) (2020)
- [RouteNet: Leveraging Graph Neural Networks for network modeling and optimization in SDN](https://mlsanity.com/paper/1910.01508/) (2019)
- [Automating Botnet Detection with Graph Neural Networks](https://mlsanity.com/paper/2003.06344/) (2020)
- [Locally Differentially Private Analysis of Graph Statistics](https://mlsanity.com/paper/2010.08688/) (2020)

## Built on by (most cited first, 16 of 16)

- [A Survey on Privacy in Graph Neural Networks: Attacks, Preservation, and Applications](https://mlsanity.com/paper/2308.16375/) (2023)
- [Deep Efficient Private Neighbor Generation for Subgraph Federated Learning](https://mlsanity.com/paper/2401.04336/) (2024)
- [ProGAP: Progressive Graph Neural Networks with Differential Privacy Guarantees](https://mlsanity.com/paper/2304.08928/) (2023)
- [Degree-Preserving Randomized Response for Graph Neural Networks under Local Differential Privacy](https://mlsanity.com/paper/2202.10209/) (2022)
- [A Privacy-Preserving Subgraph-Level Federated Graph Neural Network via Differential Privacy](https://mlsanity.com/paper/2206.03492/) (2022)
- [Only Large Weights (And Not Skip Connections) Can Prevent the Perils of Rank Collapse](https://mlsanity.com/paper/2505.16284/) (2025)
- [Blink: Link Local Differential Privacy in Graph Neural Networks via Bayesian Estimation](https://mlsanity.com/paper/2309.03190/) (2023)
- [Unveiling the Role of Message Passing in Dual-Privacy Preservation on GNNs](https://mlsanity.com/paper/2308.13513/) (2023)
- [Privacy-Preserving Graph Embedding based on Local Differential Privacy](https://mlsanity.com/paper/2310.11060/) (2023)
- [GraphPub: Generation of Differential Privacy Graph with High Availability](https://mlsanity.com/paper/2403.00030/) (2024)
- [Fair Decentralized Learning](https://mlsanity.com/paper/2410.02541/) (2024)
- [Differentially Private Graph Neural Network with Importance-Grained Noise Adaption](https://mlsanity.com/paper/2308.04943/) (2023)
- [FairGFL: Privacy-Preserving Fairness-Aware Federated Learning with Overlapping Subgraphs](https://mlsanity.com/paper/2512.23235/) (2025)
- [HoGS: Homophily-Oriented Graph Synthesis for Local Differentially Private GNN Training](https://mlsanity.com/paper/2602.08762/) (2026)
- [Auditing Privacy Risks in LLM-Enhanced Graph Neural Networks](https://mlsanity.com/paper/2608.25727/) (2026)
- [Trust-But-Verify: Poisoning-Resilient Locally Private Graph Learning Protocols](https://mlsanity.com/paper/2609.07063/) (2026)

## Abstract (arXiv)

Many real-world networks are inherently decentralized. For example, in social networks, each user maintains a local view of a social graph, such as a list of friends and her profile. It is typical to collect these local views of social graphs and conduct graph learning tasks. However, learning over graphs can raise privacy concerns as these local views often contain sensitive information. In this paper, we seek to ensure private graph learning on a decentralized network graph. Towards this objective, we propose em Solitude, a new privacy-preserving learning framework based on graph neural networks (GNNs), with formal privacy guarantees based on edge local differential privacy. The crux of em Solitude is a set of new delicate mechanisms that can calibrate the introduced noise in the decentralized graph collected from the users. The principle behind the calibration is the intrinsic properties shared by many real-world graphs, such as sparsity. Unlike existing work on locally private GNNs, our new framework can simultaneously protect node feature privacy and edge privacy, and can seamlessly incorporate with any GNN with privacy-utility guarantees. Extensive experiments on benchmarking datasets show that em Solitude can retain the generalization capability of the learned GNN while preserving the users' data privacy under given privacy budgets.