Entropy-Aware Graph Neural,Networks: Theory, Methods,,and Applications - 

Special Issue in MDPI Entropy

For submission information, please visit the SI webpage:

https://www.mdpi.com/journal/entropy/special_issues/1028YT5CB9

Submission deadline: June 30, 2026

Guest Editors: Junran Wu, Nan Wang, Friedhelm Schwenker

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. 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.

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
- provide information-theoretic analysis of GNN mechanisms and architectures,
- propose new entropy- or information-driven GNN methods, or
- explore applications of entropy-aware graph learning
in scientific, industrial, and social domains.

-- 
Prof. Dr. Friedhelm Schwenker
University of Ulm
Institute of Neural Information Processing
D-89069 Ulm, Germany
phone:  +49-731-50-24159
fax:    +49-731-50-24156
email:  friedhelm.schwenker@uni-ulm.de
www:    https://www.uni-ulm.de/in/neuroinformatik/institut/hidden/f-schwenker/