Generating a Doppelganger Graph: Resembling but Distinct

TL;DR

This paper introduces a method to generate a doppelganger graph that closely resembles a given graph in properties but has minimal edge overlap, enabling privacy-preserving data sharing for benchmarking.

Contribution

The paper presents a novel approach combining graph representation learning, GANs, and realization algorithms to generate similar yet distinct graphs from a single example.

Findings

Generated graphs match key properties of original graphs.

Edge overlap with original graphs is near zero.

Downstream node classification performance is maintained.

Abstract

Deep generative models, since their inception, have become increasingly more capable of generating novel and perceptually realistic signals (e.g., images and sound waves). With the emergence of deep models for graph structured data, natural interests seek extensions of these generative models for graphs. Successful extensions were seen recently in the case of learning from a collection of graphs (e.g., protein data banks), but the learning from a single graph has been largely under explored. The latter case, however, is important in practice. For example, graphs in financial and healthcare systems contain so much confidential information that their public accessibility is nearly impossible, but open science in these fields can only advance when similar data are available for benchmarking. In this work, we propose an approach to generating a doppelganger graph that resembles a given one in many graph properties but nonetheless can hardly be used to reverse engineer the original one, in the sense of a near zero edge overlap. The approach is an orchestration of graph representation learning, generative adversarial networks, and graph realization algorithms. Through comparison with several graph generative models (either parameterized by neural networks or not), we demonstrate that our result barely reproduces the given graph but closely matches its properties. We further show that downstream tasks, such as node classification, on the generated graphs reach similar performance to the use of the original ones.