Skip to main content
SpringerLink
Log in
Computing
Publishing model:
Hybrid

Computing - Call for Papers: Special issue on Link Prediction in Complex Networks

Special Issue on Link Prediction in Complex Networks

Theme

There are plenty of complex systems in the world that we live in – Earth’s global climate, social and economic organizations, the human brain, and transportation or communication systems, to name a few. The complex network is an indispensable theoretical tool to study the behavior of such complex systems. The nodes of a complex network correspond to different entities of a complex system, whereas, the links describe the relationship between the entities. The study of the complex networks has, therefore, become a common focus in many branches of science.

Over the years, researchers in both academia and industry have primarily focused on envisaging ubiquitous principles to tackle different types of complex networks, i.e., small world phenomenon, the structure hole, and the network centrality. Whilst such research outcomes have deepened our understanding of the complex networks from a global perspective, they, nevertheless, failed to explore the local structure of a network and the information of entities in a network. Keeping in view this challenge, many researchers have lately started to focus on the characteristics of different types of networks from the global level to (a) the mesoscopic level, i.e., community structural, and (b) micro-level, i.e., nodes and links.

Link prediction is an important network-related problem. It aims to infer new links or unknown interactions among the pairs of nodes primarily depending on their underlying properties and the currently observed links. It further explains the mechanisms of complex network structure from a micro-level perspective and can strengthen our understanding about the generation of related complex systems. However, the link prediction task in the network is challenging, particularly, in the metric design to evaluate the accuracy of the predicted links.

The objective of this Special Issue is thus to discuss and promote ideas and practices pertinent to link prediction in complex networks. Potential topics include, but are not limited, to the following:

  • Temporal Link in Evolving Networks
  • The Network Structure of Complex Networks
  • Link Prediction Techniques, Applications, and Performance
  • Applications of Link Prediction in Social Networks
  • Link Prediction across Heterogeneous Social Networks
  • Link Prediction in Social Networks
  • Knowledge Graph Embedding for Link Prediction
  • Dynamic Network Metric Evaluation
  • Information Retrieval and Text Analytics
  • Data Science and AI Technology
  • Community-level Information Diffusion with Concept Learning
  • Link Prediction in IoTUse cases and real-world applications

Special Issue Editors

Michael Sheng, Macquarie University, Sydney, Australia (michael.sheng@mq.edu.au (this opens in a new tab)) – Lead Guest Editor

Taotao Cai, Macquarie University, Sydney, Australia (taotao.cai@mq.edu.au (this opens in a new tab))

Adnan Mahmood, Macquarie University, Sydney, Australia (adnan.mahmood@mq.edu.au (this opens in a new tab))

Important Dates

Submission Deadline: February 15, 2023

Expected First Round of Revisions: April 15, 2023

Expected Second Round of Revisions: July 15, 2023

Final Notifications and Anticipated Publication: Fourth Quarter of 2023

Submission Guidelines

This Special Issue invite researchers working in the cross-cutting information and knowledge-based systems, data science, and artificial intelligence (AI) to submit original papers related to link prediction in complex networks. Both high-quality surveys and technical contributions are welcome for the Special Issue. All submissions should be supported by appropriate arguments and validation via case studies, experiments, or systematic comparisons with other approaches or benchmarks. Submissions, initial as well as final, should not exceed 25 pages.

Manuscripts that extend research published previously (e.g., in conference or workshop proceedings) will only be considered if they include at least 30% of significantly new material. The submission of such manuscripts must be accompanied by a “Summary of Differences” letter explaining how the authors extended their previously published work.

Manuscripts should follow submission guidelines available at https://www.springer.com/journal/607/submission-guidelines (this opens in a new tab).

Furthermore, the manuscripts should be submitted via the Editorial Manager platform available at https://www.editorialmanager.com/comp/default.aspx (this opens in a new tab). Please select the special issue, “S.I.: Link Prediction in Complex Networks”, from the drop-down menu within the section entitled, Additional Information, during the submission process.


Search

Navigation