Advancement of Mathematical Methods in Feature Representation Learning for Artificial Intelligence, Data Mining and Robotics, 3rd Edition

A special issue of Mathematics (ISSN 2227-7390). This special issue belongs to the section "E1: Mathematics and Computer Science".

Deadline for manuscript submissions: 31 January 2026 | Viewed by 726

Special Issue Editors


E-Mail Website
Guest Editor
College of Computer and Information Science, College of Software, Southwest University, Chongqing 400715, China
Interests: model compression; feature representation learning; deep dictionary learning; graph embedding; visual recognition
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
School of Big Data and Computer Science, Guizhou Normal University, Guiyang 550001, China
Interests: cross media analysis; computer vision; camera-based vital sign measurement; machine learning
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

The current Special Issue is devoted to the advancement of mathematical methods in artificial intelligence, data mining, and robotics. Big data have boosted the rapid development of new techniques in artificial intelligence (AI), data mining, and robotics over the past decade. However, this development has been subject to the mathematical foundation under feature representation learning in the developed models, especially the ones based on deep neural networks. Due to this, the efficiency, reliability, and security of AI models are likely to be influenced. The topic of this Special Issue covers a wide range of algorithms, methods, and applications of explainable representation learning from a mathematical perspective. Topics of interest include, but are not limited to, the following:

  • Visual recognition methods and algorithms;
  • Explainable deep learning and its applications;
  • Theory of representation learning;
  • Data mining approaches;
  • Model compression;
  • Deep dictionary learning;
  • Knowledge discovery systems;
  • Human-based computer vision.

Prof. Dr. Jianping Gou
Prof. Dr. Weihua Ou
Dr. Lan Du
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 250 words) can be sent to the Editorial Office for assessment.

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. Mathematics is an international peer-reviewed open access semimonthly 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

  • visual recognition
  • deep learning
  • knowledge distillation
  • representation learning
  • data mining

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.

Related Special Issues

Published Papers (1 paper)

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

Research

18 pages, 3244 KB  
Article
Achieving Distributional Robustness with Group-Wise Flat Minima
by Seowon Ji, Seunghyun Moon, Jiyoon Shin and Sangwoo Hong
Mathematics 2025, 13(20), 3343; https://doi.org/10.3390/math13203343 - 20 Oct 2025
Viewed by 506
Abstract
Improving robustness under distributional shifts remains a central challenge in machine learning. Although Sharpness-Aware Minimization (SAM) has proven effective in finding flatter minima for better generalization, it overlooks the heterogeneity in sharpness across different subpopulations, which can exacerbate performance gaps for minority or [...] Read more.
Improving robustness under distributional shifts remains a central challenge in machine learning. Although Sharpness-Aware Minimization (SAM) has proven effective in finding flatter minima for better generalization, it overlooks the heterogeneity in sharpness across different subpopulations, which can exacerbate performance gaps for minority or vulnerable groups. To address this challenge, we propose Group-gap Guided SAM (G2-SAM), a new optimization framework that promotes distributional robustness by steering flatness-seeking directions according to intergroup loss disparities. Our method estimates group-wise sharpness and adaptively refines perturbation strategies to minimize the worst-group loss while preserving model consistency. Through comprehensive experiments across various datasets, we show that G2-SAM achieves superior Worst-Group Accuracy and robustness, outperforming previous baselines. These findings highlight the importance of addressing group-specific geometry in the loss landscape to build more reliable and equitable neural networks. Full article
Show Figures

Figure 1

Back to TopTop