Abstract

Networks are invaluable tools to study real biological, social and technological complex systems in which connected elements form a purposeful phenomenon. A higher resolution image of these systems shows that the connection types do not confine to one but to a variety of types. Multiplex networks encode this complexity with a set of nodes which are connected in different layers via different types of links. A large body of research on link prediction problem is devoted to finding missing links in single-layer (simplex) networks. In recent years, the problem of link prediction in multiplex networks has gained the attention of researchers from different scientific communities. Although most of these studies suggest that prediction performance can be enhanced by using the information contained in different layers of the network, the exact source of this enhancement remains obscure. Here, it is shown that similarity w.r.t. structural features (eigenvectors) is a major source of enhancements for link prediction task in multiplex networks using the proposed layer reconstruction method and experiments on real-world multiplex networks from different disciplines. Moreover, we characterize how low values of similarity w.r.t. structural features result in cases where improving prediction performance is substantially hard.

Highlights

  • IntroductionReal-world networks like biochemical, human and air transportation networks are examples of biological, social and technological systems, respectively

  • Real-world systems are made of elements with complex interconnections in between

  • These studies should clarify how different layers interact to shape the function of each layer and the function of the system as a whole

Read more

Summary

Introduction

Real-world networks like biochemical, human and air transportation networks are examples of biological, social and technological systems, respectively. Scientists have studied these systems extensively under the title of complex networks or network science [1,2]. The core concept of these researches is that the collective behaviour of the whole system is not just a 2 simple superposition of individual behaviour of elements of the system [3]. These complex interactions lead to non-trivial behaviour of the whole system. Neurons, human beings and airports as the elements of aforementioned systems are linked by inter-cellular connections, acquaintances and flights, respectively, to shape the specific purposes of the systems [4,5,6]

Methods
Results
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call