The Information Bottleneck Method: Theory and 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: 31 March 2026 | Viewed by 141
Special Issue Editors
Interests: information theory of deep neural network; explainable/interpretable AI; machine learning in non-stationary environments; time series analysis; brain network analysis
Special Issues, Collections and Topics in MDPI journals
Special Issue Information
Dear Colleagues,
Deep learning models continue to face two fundamental challenges: limited generalization to out-of-distribution (OOD) data and a lack of interpretability. The information bottleneck (IB) principle, introduced by Tishby et al., offers a mathematically grounded framework to address both problems by learning data representations that are minimal yet sufficient. Over the past decade, IB has become increasingly relevant to deep learning theory, providing tools to analyze generalization, optimize training, and enhance interpretability.
This Special Issue will explore both the theoretical foundations and practical applications of the IB principle. On the theoretical side, we invite works that deepen the understanding of IB in relation to generalization, optimization, and its connections to rate–distortion theory. On the methodological side, we welcome contributions that leverage IB for loss function design, training algorithms, and architecture development, highlighting its ability to improve both robustness and explainability of deep learning models.
Finally, we particularly encourage submissions showcasing applications of IB in emerging areas such as deep reinforcement learning, self-supervised learning, multimodal learning, and learning on graph data, while also welcoming broader applications in machine learning, signal processing, and other engineering domains. By consolidating the latest ideas across disciplines, this Special Issue aims to advance the state of knowledge on the information bottleneck method and inspire new directions at the interface of information theory and artificial intelligence.
Dr. Shujian Yu
Prof. Dr. Robert Jenssen
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
- information bottleneck
- neural networks
- deep learning generalization
- explainable neural networks
- deep reinforcement learning
- multimodal learning
- self-supervised learning
- graph neural networks
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.
