# Differentially Private Graph Neural Network with Importance-Grained Noise Adaption

arXiv: https://arxiv.org/abs/2308.04943 · HTML: https://mlsanity.com/paper/2308.04943/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 57 references that are in the map.
- First posted on arXiv 9 Aug 2023.

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

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Revisiting Semi-Supervised Learning with Graph Embeddings](https://mlsanity.com/paper/1603.08861/) (2016)
- [Multi-scale Attributed Node Embedding](https://mlsanity.com/paper/1909.13021/) (2019)
- [Principal Neighbourhood Aggregation for Graph Nets](https://mlsanity.com/paper/2004.05718/) (2020)
- [Characteristic Functions on Graphs: Birds of a Feather, from Statistical Descriptors to Parametric Models](https://mlsanity.com/paper/2005.07959/) (2020)
- [Membership Inference Attack on Graph Neural Networks](https://mlsanity.com/paper/2101.06570/) (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)
- [Discrete Distribution Estimation under Local Privacy](https://mlsanity.com/paper/1602.07387/) (2016)
- [GAP: Differentially Private Graph Neural Networks with Aggregation Perturbation](https://mlsanity.com/paper/2203.00949/) (2022)
- [Estimating Node Importance in Knowledge Graphs Using Graph Neural Networks](https://mlsanity.com/paper/1905.08865/) (2019)
- [Node-Level Differentially Private Graph Neural Networks](https://mlsanity.com/paper/2111.15521/) (2021)
- [ConsisRec: Enhancing GNN for Social Recommendation via Consistent Neighbor Aggregation](https://mlsanity.com/paper/2105.02254/) (2021)
- [Releasing Graph Neural Networks with Differential Privacy Guarantees](https://mlsanity.com/paper/2109.08907/) (2021)
- [Directional Message Passing on Molecular Graphs via Synthetic Coordinates](https://mlsanity.com/paper/2111.04718/) (2021)
- [Locally Differentially Private Analysis of Graph Statistics](https://mlsanity.com/paper/2010.08688/) (2020)
- [Towards Private Learning on Decentralized Graphs with Local Differential Privacy](https://mlsanity.com/paper/2201.09398/) (2022)
- [Federated Dynamic GNN with Secure Aggregation](https://mlsanity.com/paper/2009.07351/) (2020)
- [Differentially Private Graph Classification with GNNs](https://mlsanity.com/paper/2202.02575/) (2022)
- [ProGAP: Progressive Graph Neural Networks with Differential Privacy Guarantees](https://mlsanity.com/paper/2304.08928/) (2023)
- [DPAR: Decoupled Graph Neural Networks with Node-Level Differential Privacy](https://mlsanity.com/paper/2210.04442/) (2022)
- [RDP-GAN: A R'enyi-Differential Privacy based Generative Adversarial Network](https://mlsanity.com/paper/2007.02056/) (2020)

## Abstract (arXiv)

Graph Neural Networks (GNNs) with differential privacy have been proposed to preserve graph privacy when nodes represent personal and sensitive information. However, the existing methods ignore that nodes with different importance may yield diverse privacy demands, which may lead to over-protect some nodes and decrease model utility. In this paper, we study the problem of importance-grained privacy, where nodes contain personal data that need to be kept private but are critical for training a GNN. We propose NAP-GNN, a node-importance-grained privacy-preserving GNN algorithm with privacy guarantees based on adaptive differential privacy to safeguard node information. First, we propose a Topology-based Node Importance Estimation (TNIE) method to infer unknown node importance with neighborhood and centrality awareness. Second, an adaptive private aggregation method is proposed to perturb neighborhood aggregation from node-importance-grain. Third, we propose to privately train a graph learning algorithm on perturbed aggregations in adaptive residual connection mode over multi-layers convolution for node-wise tasks. Theoretically analysis shows that NAP-GNN satisfies privacy guarantees. Empirical experiments over real-world graph datasets show that NAP-GNN achieves a better trade-off between privacy and accuracy.