Towards Private Learning on Decentralized Graphs with Local Differential Privacy

by   Wanyu Lin, et al.

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 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 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 Solitude can retain the generalization capability of the learned GNN while preserving the users' data privacy under given privacy budgets.


page 1

page 2

page 3

page 4


Towards Training Graph Neural Networks with Node-Level Differential Privacy

Graph Neural Networks (GNNs) have achieved great success in mining graph...

Privacy-Preserving Analytics on Decentralized Social Graphs: The Case of Eigendecomposition

Analytics over social graphs allows to extract valuable knowledge and in...

Gromov-Wasserstein Discrepancy with Local Differential Privacy for Distributed Structural Graphs

Learning the similarity between structured data, especially the graphs, ...

Degree-Preserving Randomized Response for Graph Neural Networks under Local Differential Privacy

Differentially private GNNs (Graph Neural Networks) have been recently s...

Shared data granularity: A latent dimension of privacy scoring over online social networks

Privacy scoring aims at measuring the privacy violation risk of a user o...

Graph-Homomorphic Perturbations for Private Decentralized Learning

Decentralized algorithms for stochastic optimization and learning rely o...

Decentralized Graph Neural Network for Privacy-Preserving Recommendation

Building a graph neural network (GNN)-based recommender system without v...

Please sign up or login with your details

Forgot password? Click here to reset