Advances in Graph Learning and Representation Models for Complex Network Analysis

Dear Colleagues,

Graph-structured data pervade numerous domains, underpinning systems and processes ranging from social and communication networks to biological pathways, financial systems, recommendation engines, and knowledge graphs. Effectively learning from and analyzing such data remains a central challenge in machine learning and network science. Recent progress in graph representation learning, such as transformer-based architectures, has significantly advanced our ability to model complex relational structures, capture long-range dependencies, and generalize across diverse graph types.

This Special Issue aims to bring together leading-edge research that explores the design, implementation, and application of graph learning and representation model. We seek to highlight both foundational innovations and practical insights that push the boundaries of what is possible in graph-based learning, with particular attention to model scalability, interpretability, and cross-domain utility.

We invite original research articles and comprehensive survey papers addressing, but not limited to, the following topics:

• Novel Graph Transformer Architectures;
• Applications of Graph Transformers;
• Scalable and Efficient Training;
• Interpretability and Explainability;
• Heterogeneous and Multi-Relational Graphs;
• Higher-order network representation and learning;
• Generative and Predictive Applications;
• Benchmarking and Evaluation;
• Ethical, Privacy, and Security Considerations.

Our aim is to assemble high-impact contributions across these topics to create a Special Issue that serves as a comprehensive resource for researchers and practitioners working at the intersection of graph learning and complex network analysis. We encourage submissions that not only demonstrate technical novelty but also articulate the broader implications of their work for science, society, and industry.

We look forward to receiving your contributions.

Dr. Enrico Corradini
Dr. Francesco Cauteruccio
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. Big Data and Cognitive Computing 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.

• graph transformers
• self-attention on graphs
• heterogeneous and multi-relational graphs
• scalable graph learning
• interpretability and explainability
• real-time graph analytics
• privacy-preserving graph methods