Inference using noisy degrees: Differentially private $\beta$-model and synthetic graphs

TL;DR

This paper develops differentially private methods for the $eta$-model of random graphs, enabling accurate inference and synthetic graph generation from noisy degree data while maintaining privacy.

Contribution

It introduces a private estimator for the $eta$-model, characterizes conditions for MLE existence, and provides algorithms for synthetic graph release with theoretical guarantees.

Findings

Private estimator is consistent and asymptotically normal.

The private method outperforms existing algorithms in real data.

The approach enables accurate, private inference from noisy degrees.

Abstract

The $\beta$-model of random graphs is an exponential family model with the degree sequence as a sufficient statistic. In this paper, we contribute three key results. First, we characterize conditions that lead to a quadratic time algorithm to check for the existence of MLE of the $\beta$-model, and show that the MLE never exists for the degree partition $\beta$-model. Second, motivated by privacy problems with network data, we derive a differentially private estimator of the parameters of $\beta$-model, and show it is consistent and asymptotically normally distributed - it achieves the same rate of convergence as the nonprivate estimator. We present an efficient algorithm for the private estimator that can be used to release synthetic graphs. Our techniques can also be used to release degree distributions and degree partitions accurately and privately, and to perform inference from noisy degrees arising from contexts other than privacy. We evaluate the proposed estimator on real graphs and compare it with a current algorithm for releasing degree distributions and find that it does significantly better. Finally, our paper addresses shortcomings of current approaches to a fundamental problem of how to perform valid statistical inference from data released by privacy mechanisms, and lays a foundational groundwork on how to achieve optimal and private statistical inference in a principled manner by modeling the privacy mechanism; these principles should be applicable to a class of models beyond the $\beta$-model.