Graph Learning and Graph Neural Networks: Techniques and Applications

Dear Colleagues,

Graph-structured data are widely used to represent complex relationships in information systems, including social networks, web networks, and scientific data. Learning from such data has therefore become an important topic in information processing research. In recent years, graph learning has attracted increasing attention due to its ability to model relational and structural information beyond traditional feature-based approaches.

This Special Issue focuses on recent research on graph learning, with an emphasis on techniques that support information processing tasks. The scope includes both theoretical and practical studies related to representation learning on graphs, pre-training and adaptation on graphs, and graph foundation models, among others.

The Special Issue further welcomes application-oriented work that demonstrates the use of graph learning in real information systems. Relevant applications include, but are not limited to, information retrieval, recommendation systems, knowledge management, network analysis, and decision support. We also encourage submissions that explore the interaction between graph learning and other learning paradigms, such as language models or reinforcement learning, as well as studies that consider model robustness, interpretability, and efficiency. We also welcome contributions that apply graph learning methods to scientific data analysis and discovery, including work related to AI for Science, where graph-based models play a key role in representing and reasoning over complex scientific systems.

The goal of this Special Issue is to provide a focused collection of recent advances in graph learning, and to reflect ongoing research efforts and open problems in this area of information processes.

Prof. Dr. Xinming Zhang
Guest Editor

Dr. Xingtong Yu
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-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Information is an international peer-reviewed open access monthly 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 1800 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.