Learning epidemic threshold in complex networks by Convolutional Neural Network

TL;DR

This paper introduces a CNN-based framework that combines structural and dynamical features of complex networks to accurately learn the epidemic threshold, outperforming existing methods on synthetic and real-world data.

Contribution

It proposes a novel approach that integrates network structure and dynamics into a CNN model using graph embedding and multi-channel images for threshold detection.

Findings

High accuracy in identifying epidemic thresholds on synthetic networks

Effective performance on empirical network datasets

Robust applicability to networks of arbitrary size and topology

Abstract

Deep learning has taken part in the competition since not long ago to learn and identify phase transitions in physical systems such as many body quantum systems, whose underlying lattice structures are generally regular as they're in euclidean space. Real networks have complex structural features which play a significant role in dynamics in them, and thus the structural and dynamical information of complex networks can not be directly learned by existing neural network models. Here we propose a novel and effective framework to learn the epidemic threshold in complex networks by combining the structural and dynamical information into the learning procedure. Considering the strong performance of learning in Euclidean space, Convolutional Neural Network (CNN) is used and, with the help of confusion scheme, we can identify precisely the outbreak threshold of epidemic dynamics. To represent the high dimensional network data set in Euclidean space for CNN, we reduce the dimensionality of a network by using graph representation learning algorithms and discretize the embedded space to convert it into an image-like structure. We then creatively merge the nodal dynamical states with the structural embedding by multi-channel images. In this manner, the proposed model can draw the conclusion from both structural and dynamical information. A large number of simulations show a great performance in both synthetic and empirical network data set. Our end-to-end machine learning framework is robust and universally applicable to complex networks with arbitrary size and topology.