Trustworthy Graph Learning Systems

Dear Colleagues,

We are pleased to invite you to submit your latest research to the upcoming Special Issue on “Trustworthy Graph Learning Systems”, edited by Dr. He Zhang (Griffith University, Australia), A/Prof. Luzhi Wang (Dalian Maritime University, China), Assistant Professor Jian Kang (Mohamed bin Zayed University of Artificial Intelligence, United Arab Emirates) and Associate Professor Leo Zhang (Griffith University, Australia).

Graph learning has become a fundamental technique for modeling relational data across numerous domains, including social networks, recommender systems, biological networks, cybersecurity, and scientific discovery. Recent advances in large language models (LLMs) and graph foundation models have further expanded the capabilities of graph learning, enabling enhanced graph representation, reasoning, and knowledge discovery. As graph learning systems are increasingly deployed in real-world applications, ensuring their trustworthiness has become a critical research challenge. This Special Issue aims to bring together recent advances in developing trustworthy graph learning systems, covering fundamental methodologies, emerging LLM-enabled graph learning paradigms, system-level considerations, and practical applications.

We welcome original research articles and comprehensive surveys on, but not limited to, the following topics:

• Trustworthy graph learning and graph foundation models.
• Trustworthy LLM-enhanced graph learning and graph reasoning.
• Robustness, adversarial learning, and graph security.
• Privacy-preserving graph learning and graph unlearning.
• Explainability, interpretability, and accountability in graph learning.
• Fairness and responsible graph AI.
• Generalization, transfer learning, and out-of-distribution learning on graphs.
• Trustworthiness evaluation, benchmarking, and certification for graph learning systems.
• Scalable deployment, secure infrastructures, and lifecycle management of graph learning systems.
• Trustworthy graph learning for real-world applications.
• Cross-disciplinary studies of AI for graph-based applications focused on trustworthiness.
• Other emerging topics related to trustworthiness and graph-related systems.

The Guest Editors have broad research expertise spanning graph learning, graph mining, data mining, recommender systems, personalization, generative AI, and trustworthy AI. Their research covers robustness, privacy, fairness, explainability, secure graph learning, large language models, diffusion and flow models, and other emerging trustworthiness topics. This Special Issue aims to provide a timely forum for researchers and practitioners to present recent advances and discuss future directions in trustworthy graph learning systems, including their trustworthy development, deployment, and management.

We sincerely invite you to consider submitting your latest work and would greatly appreciate it if you could also share this Call for Papers with colleagues and researchers who may be interested.

If you have any questions regarding the suitability of your manuscript, please feel free to contact the Guest Editors.

We look forward to receiving your valuable submissions.

Best regards,

Dr. He Zhang
Dr. Luzhi Wang
Dr. Kang Jian
Dr. Leo (Yu) Zhang
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-anonymized 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.

• trustworthy graph learning
• graph neural networks
• robustness
• privacy
• unlearning
• explainability
• fairness
• graph security
• out-of-distribution detection
• generalization
• trustworthiness evaluation