Graph Learning Methods in Data Science with Applications

Dear Colleagues,

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 your contributions providing a valuable resource for researchers and practitioners alike, promoting innovation in this constantly evolving and impactful area.

Dr. Marco Podda
Guest Editor

Dr. Daniele Castellana
Guest Editor Assistant

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-anonymized peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Mathematics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.