Special issue on Graph Machine Learning

Existing works on graph machine learning, especially on graph neural network (GNN), are typically for conventional graphs. In many emerging applications (such as in ecommerce, social networks and bioinformatics), however, the graph interactions are beyond general attributed graphs and are more complex. For example, the e-commerce search interactions can be better modelled as text-rich graphs where nodes information is semantic text rather than features; the sequence dependence data (such as click-streams where the choice of the next page depends not only on the current page but also on previous pages) can be better modelled as higher-order dependency graphs rather than the conventional first-order graphs. This brings a big challenge and new research topics in graph-based pattern recognition. So, in this special issue we will focus on graph-based pattern recognition with machine learning on more complex and heterogeneous graphs, such as text-rich graphs, multi-relational graphs, heterophilic graphs, higher-order dependency graphs, spatio-temporal graphs, bipartite graphs, signed graphs and hypergraphs [1, 2], as well as their emerging applications in ecommerce, biometrics /bioinformatics, CV and NLP [3]. Papers are invited on but not limited to new models, algorithms, theories and applications, and bring both researchers from academia and practitioners from industry to discuss the latest progress, new ideas and advanced applications under this new topic.

Important Dates:
Submission Portal Open: September 30, 2022
Final Date for Submission: March 31, 2023
Final Date for Acceptance: July 31, 2023

Guest editors:
Di Jin, Tianjin University, jindi@tju.edu.cn
Shirui Pan, Griffith University, shiruipan@ieee.org
Weiping Ding, Nantong University, ding.wp@ntu.edu.cn
Kaska Musial, University of Technology Sydney, katarzyna.musial-gabrys@uts.edu.au
Francoise Soulie, Hub France IA, francoise.soulie@outlook.com
Philip Yu, University of Illinois at Chicago, psyu@uic.edu

Manuscript submission information:
Prospective authors are invited to submit their papers via the online submission system at https://www.editorialmanager.com/pr/default1.aspx , under article type VSI: Graph Machine Learning

Keywords:
graph machine learning/GNN; heterogeneous graphs; text-rich graphs; heterophilic graphs; higher-order graphs; spatio-temporal graphs; hypergraphs; community detection; ecommerce search/recommendation; traffic flow prediction

Learn more about the benefits of publishing in a special issue: https://www.elsevier.com/authors/submit-your-paper/special-issues

Interested in becoming a guest editor? Discover the benefits of guest editing a special issue and the valuable contribution that you can make to your field: https://www.elsevier.com/editors/role-of-an-editor/guest-editors