English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Deep learning models are known to put the privacy of their training data atrisk, which poses challenges for their safe and ethical release to the public.Differentially private stochastic gradient descent is the de facto standard fortraining neural networks without leaking sensitive information about thetraining data. However, applying it to models for graph-structured data poses anovel challenge: unlike with i.i.d. data, sensitive information about a node ina graph cannot only leak through its gradients, but also through the gradientsof all nodes within a larger neighborhood. In practice, this limitsprivacy-preserving deep learning on graphs to very shallow graph neuralnetworks. We propose to solve this issue by training graph neural networks ondisjoint subgraphs of a given training graph. We develop threerandom-walk-based methods for generating such disjoint subgraphs and perform acareful analysis of the data-generating distributions to provide strong privacyguarantees. Through extensive experiments, we show that our method greatlyoutperforms the state-of-the-art baseline on three large graphs, and matches oroutperforms it on four smaller ones.

Training Differentially Private Graph Neural Networks with Random Walk Sampling