Estimating the dynamics of kernel-based evolving networks

TL;DR

This paper introduces a new methodology for analyzing the evolution of networks like citation and collaboration graphs by extracting a kernel function that models their dynamic growth and decay processes.

Contribution

The paper presents a novel approach to determine the attachment kernel from network history, enabling better understanding of network dynamics.

Findings

Kernel function can be extracted from network history.

Method applied to scientific citation and collaboration networks.

Provides insights into network growth and decay processes.

Abstract

In this paper we present the application of a novel methodology to scientific citation and collaboration networks. This methodology is designed for understanding the governing dynamics of evolving networks and relies on an attachment kernel, a scalar function of node properties, which stochastically drives the addition and deletion of vertices and edges. We illustrate how the kernel function of a given network can be extracted from the history of the network and discuss other possible applications.