Model-based reconstruction of real-world fractal complex networks

TL;DR

This paper introduces a flexible, stochastic model for generating fractal complex networks that accurately replicate key properties of real-world systems like the Internet and co-authorship networks.

Contribution

It combines reverse renormalization and evolving network models with tunable parameters to better mimic the topology and scaling behaviors of natural and man-made networks.

Findings

Successfully reproduces fractal dimensions and power-law degree distributions.

Captures scale-invariant properties of hierarchical networks.

Demonstrates applicability to real-world networks like the Internet and Web.

Abstract

This paper presents a versatile model for generating fractal complex networks that closely mirror the properties of real-world systems. By combining features of reverse renormalization and evolving network models, the proposed approach introduces several tunable parameters, offering exceptional flexibility in capturing the diverse topologies and scaling behaviors found in both natural and man-made networks. The model effectively replicates their key characteristics such as fractal dimensions, power-law degree distributions, and scale-invariant properties of hierarchically nested boxes. Unlike traditional deterministic models, it incorporates stochasticity into the network growth process, overcoming limitations like discontinuities in degree distributions and rigid size constraints. The model's applicability is demonstrated through its ability to reproduce the structural features of real-world fractal networks, including the Internet, the World Wide Web, and co-authorship networks.