Advances in Learning on Graphs and Information Networks

Dear Colleagues,

This Special Issue explores cutting-edge developments in machine learning techniques applied to graph-structured data and information networks. As our world becomes increasingly interconnected, the ability to effectively analyze and learn from complex relational data structures has become paramount across diverse domains. As more complex relationships between entities are being modeled, advancements in learning methods for graphs and networks are increasingly relevant across a wide range of applications.

This Special Issue brings together cutting-edge research that explores the latest advancements in learning algorithms, representation techniques, and their applications in graph-structured data and information networks. Key topics include:

• Graph Neural Networks (GNNs): enhancements in graph-based deep learning models, including novel architectures and training techniques that improve scalability, interpretability, and performance.
• Graph Embeddings: innovations in generating low-dimensional representations of nodes and entire graphs, facilitating more efficient processing and analysis of large-scale networks.
• Graph-based Semi-Supervised and Unsupervised Learning: methods leveraging the structure of graphs to improve learning in scenarios with limited labeled data or without labels.
• Applications in Complex Networks: the application of graph learning in domains such as healthcare, social media, organizational networks, financial systems, and infrastructure networks.
• Dynamic and Temporal Graph Learning: new models and algorithms designed to handle evolving graphs and dynamic information networks where the relationships between nodes change over time.
• Explainability and Fairness in Graph Learning: approaches to making graph-based models more interpretable and fair, particularly in sensitive applications where biases and ethical considerations must be addressed.

This Special Issue seeks to showcase the latest innovations and foster discussions that push the boundaries of learning in relation to graphs and information networks, aiming to bridge the gap between theory and practical applications in this rapidly evolving field.

Dr. Danushka Bandara
Dr. Soumyakant Padhee
Dr. Koray Ozcan
Guest Editors

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 100 words) can be sent to the Editorial Office for announcement on this website.

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. Electronics 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 2400 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.

• graph neural networks (GNNs)
• graph embeddings
• semi-supervised learning
• dynamic graphs
• scalability of graph learning