Graph Neural Networks and Its Applications

Dear Colleagues,

The burgeoning field of Knowledge Graphs (KGs) and their applications are revolutionizing numerous domains. In particular, graph neural networks (GNNs) have emerged as powerful tools in leveraging the structure and semantics of KGs. By representing entities as nodes and their relationships as edges, KGs can encapsulate vast amounts of structured and unstructured information in a unified framework. GNNs excel in extracting intricate patterns and latent representations from these interconnected data structures.

In the field of Knowledge Graphs, GNNs offer a multitude of applications and promising prospects. For instance, they facilitate more accurate entity and relation predictions, which is pivotal for tasks such as knowledge completion and link prediction within KGs. Furthermore, GNNs enable effective entity and relation classifications, aiding in tasks like entity type inference and semantic role labeling. Additionally, GNNs empower KGs reasoning by enabling sophisticated graph-based inferences, allowing for advanced query answering and knowledge discovery.

However, the exploitation of KGs for intelligent applications necessitates addressing several challenges. Privacy and security concerns are prominent, especially when KGs incorporate sensitive information from diverse sources, and robust mechanisms for preserving the confidentiality and integrity of KG data are imperative. Moreover, ensuring scalability and efficiency in GNN-based KG applications remains a crucial area of research, and techniques for optimizing GNNs' training and inference processes on large-scale KGs are of paramount importance.

This Special Issue aims to provide a comprehensive exploration of the latest advancements in GNNs and Knowledge Graphs, with a focus on security, privacy, and scalability aspects. Contributions covering both theoretical foundations and practical implementations are encouraged. Interdisciplinary studies that integrate insights from graph theory, machine learning, and database management are particularly welcome.

Topics of interest include but are not limited to the following:

• Privacy-preserving GNN architectures for sensitive KG data.
• Scalable and efficient training techniques for GNNs on large-scale KGs.
• Mechanisms for ensuring data integrity and trustworthiness in KGs.
• Novel approaches for entity and relation predictions within KGs using GNNs.
• Techniques for enhancing the interpretability and explainability of GNN-based KG models.
• GNN-based KG reasoning methods for advanced knowledge discovery and inference.
• GNN recommendation frameworks based on large-scale KGs.
• Case studies and experience reports on real-world deployments of GNNs in Knowledge Graphs.

We look forward to receiving your innovative contributions to and insights on this rapidly evolving field.

Dr. Yifei Xu
Dr. Dongjing Wang
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. Future Internet 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 1600 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 for sequence behavior modeling
• graph neural networks for personalized recommendation
• graph neural networks for spatial-temporal data prediction
• graph neural networks for traffic forecasting
• graph neural networks for medical diagnosis and analysis
• graph neural networks for electronic health
• graph neural networks for skeleton data analysis and action recognition
• graph neural networks for natural language and programming language processing