Revealing Network Structure, Confidentially: Improved Rates for Node-Private Graphon Estimation

arXiv1810.02183MaRDI QIDQ6307697FDOQ6307697

Authors: Christian Borgs, Jennifer T. Chayes, Adam Smith, Ilias Zadik 

Publication date: 4 October 2018

Abstract: Motivated by growing concerns over ensuring privacy on social networks, we develop new algorithms and impossibility results for fitting complex statistical models to network data subject to rigorous privacy guarantees. We consider the so-called node-differentially private algorithms, which compute information about a graph or network while provably revealing almost no information about the presence or absence of a particular node in the graph. We provide new algorithms for node-differentially private estimation for a popular and expressive family of network models: stochastic block models and their generalization, graphons. Our algorithms improve on prior work, reducing their error quadratically and matching, in many regimes, the optimal nonprivate algorithm. We also show that for the simplest random graph models ($G(n,p)$ and $G(n,m)$), node-private algorithms can be qualitatively more accurate than for more complex models---converging at a rate of $frac1epsilo{n}^2{n}^3$ instead of $frac1epsilo{n}^2{n}^2$. This result uses a new extension lemma for differentially private algorithms that we hope will be broadly useful.

This page was built for publication: Revealing Network Structure, Confidentially: Improved Rates for Node-Private Graphon Estimation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6307697)