Node-private community estimation in stochastic block models: Tractable algorithms and lower bounds

TL;DR

This paper develops polynomial-time algorithms for community detection in stochastic block models that are stable under node-wise privacy constraints, introducing novel methods and bounds for node-private community estimation.

Contribution

It introduces new private algorithms based on sampling and graph smoothing, along with lower bounds on privacy parameters, advancing node-private community detection.

Findings

Algorithms achieve polynomial-time complexity.

Novel lower bounds on privacy parameter growth.

Application of HGR maximal correlation in PAC learning.

Abstract

We study the classical problem of community recovery in stochastic block models with a fixed number of communities, with a twist: We seek algorithms that are stable with respect to node-wise changes in the graph structure, formally defined as a differential privacy constraint. The algorithms we develop are based on spectral clustering, where we introduce privacy to the community recovery pipeline in the form of directly privatizing the adjacency matrix; private PCA; private convex optimization; private low-rank matrix estimation; and private approximate subspace estimation. Straightforward applications of existing private algorithms lead to a rapid increase in the privacy parameter $\epsilon$ in order to ensure consistent estimation under node differential privacy, in contrast with the simpler setting of edge privacy. To alleviate these issues, we develop novel algorithms based on (1) sampling from an exponential mechanism with a Lipschitz extension and (2) a general framework for constructing smooth projections from the space of undirected graphs to the space of bounded-degree graphs, which can then be combined with various edge-private algorithms. Importantly, the methods we develop are all computable in polynomial-time as a function of the number of nodes in the graph. We also develop novel lower bounds on the growth rate of $\epsilon$ required in order to achieve consistent community estimation under node privacy. On a technical note, our paper highlights the complications that arise when analyzing private algorithms under the non-standard scaling $\epsilon \rightarrow \infty$ and proposes some solutions. We also provide a novel application of the HGR maximal correlation from information theory in the context of accuracy amplification in PAC learning, which may be of independent interest.