DPNE: Differentially private network embedding

Graph embedding and privacy, Differential privacy

We show that with only adding a small amount of noise onto the objective function, the learned low-dimensional representations satisfy differential privacy.

The definition of the differential privacy in this paper is following (see Dwork2006calibrating, Laplace distribution):

A graph analysis mechanism satisfies ε-differential privacy, if for all neighboring graphs G and G′ and all subsets Z of ’s range:

where G’ has extra (differed) edges.