Journal Browser

Journal Browser

Entropy-Centric Intelligent Computation with Graph: In Pursuit of Advanced Computational Theories, Methods, and Applications

A special issue of Entropy (ISSN 1099-4300). This special issue belongs to the section "Multidisciplinary Applications".

Deadline for manuscript submissions: 10 August 2024 | Viewed by 663

Special Issue Editors

E-Mail Website
Guest Editor
College of Computer and Information Science, Southwest University, Chongqing 400715, China
Interests: textual data mining; knowledge graphs; graph representation learning; code understanding and representation
Special Issues, Collections and Topics in MDPI journals
School of Computer Science and Technology, University of Science and Technology of China (USTC), Hefei 230027, China
Interests: data mining; graph neural networks; graph representation learning; recommendation system; network embedding
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
College of Computer Science and Software Engineering, Shenzhen University, Shenzhen 518052, China
Interests: recommendation system; graph neural network theory
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Entropy-centric intelligent computation is essential to dealing with diverse forms of graph computation issues, such as link prediction, graph classification, graph matching, graph structure learning, graph generation, and transformation. This method can be applied in a variety of different settings, including knowledge graphs, social networks, spatio-temporal networks, IoT sensing, recommendation system, self-driving cars, bioinformatics, and medical informatics.

Recently, structural entropy-based methods have been adopted to efficiently rank graph nodes. Likewise, graph entropy-based methods are employed to automatically embed dimension selection when learning different types of graph representation from the perspective of the minimum entropy principle. Furthermore, there has been a recent ware of information bottleneck-based methods developed to optimally balance the expressiveness and robustness of the learned graph representation, recognize predictive graph substructures, conduct highly efficient graph training with optimizing adversarial graph augmentation strategies, etc.

However, despite these successes, as a promising entropy-centric graph analysis and computing paradigm, significantly challenging issues still exist, such as how to model existing diverse graph structure-based data that often represent multi-modal, multi-relational, and dynamic graphs from the perspective of the entropy principle, or how to efficiently learn the neural graph representation of the large-scale field-specific graph to use its rich structural and semantic information to guide the entropy principle. Besides, it is also necessary to investigate how new entropy-centric computing theories, technologies, and novel applications might be integrated into the current and future graph computation framework.

This Special Issue will be a forum for researchers working on mining and learning from entropy-centric intelligent computation with graphs in pursuit of advanced computational theories, methods, and applications. Submitted research papers and comprehensive reviews should focused on the following research areas:

  • Entropy-centric intelligent computation theories with graphs;
  • Entropy-centric graph structured-based data modeling with time-evolving, multi-relational, and multi-modal nature;
  • Neural graph representation learning for homogeneous or heterogeneous graphs in the guidance of the entropy principle;
  • Entropy-centric data mining for knowledge graphs, linguistics graphs, bibliographic graphs, textual graphs, social networks, traffic networks, and molecules;
  • New entropy-centric computing framework/method for graph structure-based data;
  • Applications of entropy-centric graph mining in e-commerce, text mining, stock prediction, recommendation systems, self-driving cars, protein modeling, program analysis, etc.

Dr. Yongpan Sheng
Dr. Hao Wang
Dr. Junyang Chen
Dr. Chunwei Tian
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.


  • entropy-centric intelligent computation with graph
  • entropy-centric intelligent computation theories
  • entropy-centric graph/network representation learning
  • entropy-centric graph applications

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:


23 pages, 3411 KiB  
Code Similarity Prediction Model for Industrial Management Features Based on Graph Neural Networks
by Zhenhao Li, Hang Lei, Zhichao Ma and Fengyun Zhang
Entropy 2024, 26(6), 505; https://doi.org/10.3390/e26060505 - 9 Jun 2024
Viewed by 378
The code of industrial management software typically features few system API calls and a high number of customized variables and structures. This makes the similarity of such codes difficult to compute using text features or traditional neural network methods. In this paper, we [...] Read more.
The code of industrial management software typically features few system API calls and a high number of customized variables and structures. This makes the similarity of such codes difficult to compute using text features or traditional neural network methods. In this paper, we propose an FSPS-GNN model, which is based on graph neural networks (GNNs), to address this problem. The model categorizes code features into two types, outer graph and inner graph, and conducts training and prediction with four stages—feature embedding, feature enhancement, feature fusion, and similarity prediction. Moreover, differently structured GNNs were used in the embedding and enhancement stages, respectively, to increase the interaction of code features. Experiments with code from three open-source projects demonstrate that the model achieves an average precision of 87.57% and an F0.5 Score of 89.12%. Compared to existing similarity-computation models based on GNNs, this model exhibits a Mean Squared Error (MSE) that is approximately 0.0041 to 0.0266 lower and an F0.5 Score that is 3.3259% to 6.4392% higher. It broadens the application scope of GNNs and offers additional insights for the study of code-similarity issues. Full article
Back to TopTop