82
87

Private Graphon Estimation for Sparse Graphs

Abstract

We design algorithms for fitting a high-dimensional statistical model to a large, sparse network without revealing sensitive information of individual members. Given a sparse input graph GG, our algorithms output a node-differentially-private nonparametric block model approximation. By node-differentially-private, we mean that our output hides the insertion or removal of a vertex and all its adjacent edges. If GG is an instance of the network obtained from a generative nonparametric model defined in terms of a graphon WW, our model guarantees consistency, in the sense that as the number of vertices tends to infinity, the output of our algorithm converges to WW in an appropriate version of the L2L_2 norm. In particular, this means we can estimate the sizes of all multi-way cuts in GG. Our results hold as long as WW is bounded, the average degree of GG grows at least like the log of the number of vertices, and the number of blocks goes to infinity at an appropriate rate. We give explicit error bounds in terms of the parameters of the model; in several settings, our bounds improve on or match known nonprivate results.

View on arXiv
Comments on this paper