Trustworthy AI for Graph Learning and Application

Dear Colleagues,

In the era of big data, graphs have emerged as a fundamental data structure for representing complex relationships and interactions across various domains. This powerful framework has facilitated the modeling of complex systems, ranging from social networks to biological pathways, and from financial transactions to transportation networks. The integration of artificial intelligence (AI) with graph learning has catalyzed remarkable progress in numerous fields, including but not limited to social network analysis, recommendation systems, financial fraud detection, and beyond. These advancements have transformed the way we process, analyze, and interpret graph-based data, leading to improved decision-making capabilities and enhanced operational efficiencies.

As the proliferation of AI in graph-based applications continues to accelerate at an unprecedented pace, ensuring the trustworthiness of these systems has become a critical imperative. Trustworthiness encompasses a multitude of dimensions, including robustness against adversarial attacks, explainability of AI decisions, adherence to ethical principles, safeguarding of security, and protection of user privacy. Addressing these aspects is essential to foster user confidence, ensure regulatory compliance, and mitigate potential risks associated with AI-driven graph analysis.

This Special Issue seeks to serve as a platform for researchers, practitioners, and policymakers to converge and delve into the multifaceted challenges and opportunities presented by the development of trustworthy AI for graph learning and its diverse applications. We cordially invite original research papers that delve deeply into the key facets of trustworthiness within the context of graph-based AI systems. Contributions may explore innovative approaches to enhance the robustness of graph neural networks, develop explainable AI models that elucidate decision-making processes, examine ethical considerations and their implications, propose secure and privacy-preserving algorithms, or investigate any other pertinent aspect that contributes to the overall trustworthiness of AI in graph-related domains.

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

• Robust graph neural networks;
• Explainable graph learning models;
• Ethical considerations in graph learning;
• Graph-based trustworthy recommendations;
• Scalable trustworthy graph processing;
• Human–AI collaboration in graph tasks;
• Trusted applications of graph learning.

Dr. Yonghui Xu
Prof. Dr. Lianyong Qi
Dr. Hanrui Wu
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 learning
• trustworthy AI
• explainable AI
• data privacy
• robustness
• fairness