Entropy-Aware Graph Neural Networks: Theory, Methods, and Applications
A special issue of Entropy (ISSN 1099-4300). This special issue belongs to the section "Multidisciplinary Applications".
Deadline for manuscript submissions: 30 June 2026 | Viewed by 13
Special Issue Editors
Interests: graph neural networks; structural entropy; out-of-distribution detection; anomaly detection; financial time series; social network
Interests: artificial neural networks; pattern recognition; cluster analysis; statistical learning theory; data mining; multiple classifier systems; sensor fusion; affective computing
Special Issues, Collections and Topics in MDPI journals
Interests: hypergraph; graph neural network; network security anomaly detection; attack tracing
Special Issues, Collections and Topics in MDPI journals
Special Issue Information
Dear Colleagues,
Graph neural networks (GNNs) have emerged as a fundamental framework for learning from graph-structured data, demonstrating remarkable success across domains such as social network analysis, recommender systems, bioinformatics, and financial modeling. Despite their empirical success, the theoretical understanding of GNNs, particularly from the perspective of information theory, remains limited. As GNN architectures become increasingly deep, dynamic, and heterogeneous, issues related to information loss, over-smoothing, and representation degradation call for a principled, entropy-based perspective.
Entropy and information-theoretic principles provide a natural lens for analyzing the expressivity, generalization, and robustness of GNNs. From the viewpoint of Fisher information, mutual information, and information bottlenecks, entropy-aware frameworks can help explain and improve the propagation, compression, and preservation of structural information in networks. Moreover, integrating information geometry and Riemannian representations with GNNs offers new theoretical and algorithmic insights into stability, optimization, and representation learning.
This Special Issue aims to advance the understanding of entropy-aware graph neural networks by bridging information theory and graph representation learning. We invite original research and review articles that (1) provide information-theoretic analysis of GNN mechanisms and architectures, (2) propose new entropy- or information-driven GNN methods, or (3) explore applications of entropy-aware graph learning in scientific, industrial, and social domains.
Dr. Junran Wu
Prof. Dr. Friedhelm Schwenker
Dr. Nan 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. Entropy 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 2600 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.
Keywords
- graph neural networks
- information theory in graph learning
- entropy and information bottleneck
- fisher information and Riemannian geometry
- mutual information estimation on graphs
- information-theoretic regularization
- over-smoothing and entropy loss
- representation learning and graph compression
- entropy-based optimization in deep GNNs
- applications in finance, biology, social networks, etc.
Benefits of Publishing in a Special Issue
- Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
- Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
- Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
- External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
- Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.
Further information on MDPI's Special Issue policies can be found here.
