A study of fitness functions for reconstructing networks using node degrees

Evolutionary algorithms are powerful tools for optimizing problems, and their performance in various fields is a continuous subject of research. Network reconstruction is the problem of trying to discover the original structure of an existing network using limited information. In this paper, we atte...

Full description

Saved in:
Bibliographic Details
Published in2016 IEEE Congress on Evolutionary Computation (CEC) pp. 2558 - 2564
Main Authors Wimmers, Martin O., Jing Liu
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.07.2016
Subjects
Algorithm design and analysis
Electronic mail
Evolutionary computation
Image reconstruction
Optimization
Transforms
Online AccessGet full text
DOI10.1109/CEC.2016.7744108

Cover

More Information
Summary:Evolutionary algorithms are powerful tools for optimizing problems, and their performance in various fields is a continuous subject of research. Network reconstruction is the problem of trying to discover the original structure of an existing network using limited information. In this paper, we attempt to explore the ability of evolutionary algorithms to reconstruct networks by using the degree of each node as the available information. To achieve this, we introduce a novel method of representing networks with each edge being a value that corresponds to the likelihood of its existence. Moreover, we design two fitness functions that only use the degree of each node to determine the reconstruction quality, and analyze and compare them using fitness landscape and schema analysis for small networks, and verify the performance using two evolutionary algorithms for larger networks.
DOI:10.1109/CEC.2016.7744108