Recent Advances in Graph Neural Networks and Their Applications

Dear Colleagues,

Graph Neural Networks (GNNs) have emerged as a pivotal branch of artificial intelligence, specifically designed to capture the rich relational information inherent in non-Euclidean data. This Special Issue is dedicated to showcasing the latest breakthroughs in GNNs, underscoring their transformative role across the entire information processing pipeline. We welcome contributions that push the boundaries of information theory and methodology through novel GNN architectures, enhance information intelligence with advanced graph-based learning algorithms, optimize information processes for graph-structured data, and demonstrate impactful information applications in real-world scenarios. The goal of this Special Issue is to present a collection of high-quality research that addresses both the theoretical foundations and practical challenges of GNNs, solidifying their position as a cornerstone of modern information science.

Key Topics:
We invite the submission of original research and comprehensive review articles that align with the journal's scope and explore themes including, but not limited to, the following:

• Theoretical and Methodological Innovations:
  • Novel GNN architectures (e.g., Transformers for graphs, self-supervised learning on graphs).
  • Explainability and fairness in GNNs.
  • Synergies between GNNs, large language models, and structured world models.
  • Theoretical analysis of the expressive power and scalability of GNNs.
• Enhanced Information Intelligence:
  • Knowledge graph reasoning and completion.
  • Graph representation learning for complex networks.
  • Integration of GNNs with other AI paradigms (e.g., deep learning, reinforcement learning).
• Efficient Information Processes:
  • Scalable algorithms for large-scale graph processing.
  • Graph data mining and information extraction techniques.
  • Dynamic and temporal graph modeling.
• Pioneering Information Applications:
  • Social Network Analysis: Community detection, influence maximization.
  • Recommendation Systems: Leveraging user–item interaction graphs.
  • Financial Technology: Fraud detection, risk assessment.
  • Urban Computing: Traffic forecasting, infrastructure planning.

This Special Issue will serve as a valuable resource for researchers and practitioners, providing a state-of-the-art overview of how GNNs are revolutionizing the way we process, understand, and leverage interconnected information.

Dr. Jian Yu
Dr. Xin Liu
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 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.