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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

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

Differentially Private Graph Neural Network with Importance-Grained Noise Adaption