Special Issue on Graph Learning Methods in Data Science with Applications

Gennaio 7, 2025
By Daniele Castellana

Dear Colleagues,
We are pleased to invite you to submit your original contributions to the special issue:

Graph Learning Methods in Data Science with Applications

Journal: Mathematics (ISSN 2227-7390)   
Deadline for manuscript submissions: 10 September 2025
Special issue webpage


Overview

Graphs offer a concise and elegant framework for encoding and managing an ever-growing body of relational knowledge across a variety of domains such as cheminformatics, bioinformatics, social networks analysis, traffic forecasting, digital health, and computational medicine. In recent years, graph learning methods have emerged as an essential technology in data science due to their ability to analyze this wealth of information; this has enabled the realization of accurate inference and decision-making by explicitly modeling the relationships among data objects during the learning process.

This Special Issue aims to provide an overview of recent methodological advancements in graph learning for data science. The scope of this Special Issue includes, but is not limited to, the following topics:

– Graph neural networks;
– Graph representation learning;
– Bayesian methods for graphs;
– Reservoir computing for graphs;
– Kernels for graphs;
– Learning on dynamic and temporal graphs;
– Learning on multi-relational and heterogeneous graphs;
– Continual learning on graphs;
– Adversarial attacks on graphs;
– Graph generation.

In addition to methodological advancements, this Special Issue welcomes contributions that address the application of graph learning methods across various domains. Key areas of focus include, but are not limited to, the following:

– Cheminformatics and materials science;
– Bioinformatics and systems biology;
– Traffic forecasting, social and complex network analysis;
– Computational medicine and digital health.

We anticipate that your contributions will provide a valuable resource for researchers and practitioners alike, promoting innovation in this constantly evolving and impactful area.

Dr. Marco Podda
Dr. Daniele Castellana
Guest Editors

Discussione

0 commenti

Invia un commento

GRIN Società Informatica Italiana

Associazione senza scopo di lucro

Sede ufficiale

Dipartimento di Informatica dell’Università di Pisa

Partita IVA e C.F.

123454323

© 2024 GRIN Società Informatica Italiana, All Rights Reserved – P.Iva: 000000 – Design by Declar