Information-Theoretic Guided Methods for Information Network Mining and Its Applications
A special issue of Entropy (ISSN 1099-4300). This special issue belongs to the section "Information Theory, Probability and Statistics".
Deadline for manuscript submissions: 30 June 2024 | Viewed by 250
Special Issue Editors
Interests: textual data mining; knowledge graphs; graph representation learning; code understanding and representation
Special Issues, Collections and Topics in MDPI journals
Interests: data mining; graph neural networks; graph representation learning; recommendation system; network embedding
Special Issues, Collections and Topics in MDPI journals
Interests: data management; data mining; cohesive subgraph searching; graph embedding; graph neural networks; keyword searching; trajectory computing
Special Issues, Collections and Topics in MDPI journals
Special Issue Information
Dear Colleagues,
Information theory has shown impressive capabilities to augment structure information and semantic information for improving graph representation learning performance. Robust information networks, such as graph entropy-based methods, have been employed to automatic node-embedding dimension selection when learning different types of graph representation from the perspective of the minimum entropy principle. Mutual information-based methods have been introduced to structuring graphs and semantic enrichment with mutual information maximization. The recent wave of information bottleneck-based methods have attempted to optimally balance the expressiveness and robustness of learned graph representation; recognize predictive graph substructures; conduct highly efficient graph training with optimizing adversarial graph augmentation strategies; and so forth. Despite these advances, as a promising information network modeling paradigm, information-theoretic guided methods for information networks are also facing new challenges, such as how to measure and enhance structure information and semantic information for multi-modal, multi-relational, and dynamic graph analysis under the guidance of information theory; how to effectively learn with limited labels on information theory-based information networks; and how to better incorporate information-theoretic knowledge to the information network, which is also of significance in solving sophisticated problems with more promising performance.
This Special Issue is a forum for researchers from a variety of fields working on information-theoretic guided mining and learning methods for information networks to share and discuss their latest findings. It welcomes original algorithmic, methodological, theoretical, statistical, or systems-based contributions to information theory-based information network research and, in particular, applications broadly related to knowledge graphs, social networks, stock prediction, online shopping, recommendation systems, self-driving cars, bioinformatics, and medical informatics. The research papers and comprehensive reviews should focus on (but are not restricted to) the following research areas:
- Information theory-based network/graph representation learning methods for homogeneous or heterogeneous information networks;
- Information-theoretic measures and enhancement for multi-modal, multi-relational, and dynamic graph analysis;
- Entropy-theoretic-guided graph transformers and graph convolutional neural networks;
- Entropy-based data mining for knowledge graphs, linguistics graphs, bibliographic graphs, textual graphs, social networks, traffic networks, and molecules;
- Parallel computing for information theory-based information network analysis;
- The visual searching and browsing of information theory-based information networks;
- Applications of information theory-based information network mining in e-commerce, text mining, stock prediction, recommendation systems, self-driving cars, bioinformatics and medical informatics, and so on;
- Information theory-based information networks for explainable AI.
Dr. Yongpan Sheng
Dr. Hao Wang
Dr. Yixiang Fang
Guest Editors
Dr. Lirong He
Guest Editor Assistant
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
- information theory-based information networks
- information theory-based network/graph representation learning
- information theory-based information network applications
- information theory for explainable AI
Related Special Issue
- Information Network Mining and Applications in Entropy (15 articles)
