Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
5.3
2.2
Journals
Symmetry
Special Issues
Symmetry and Asymmetry in Machine Learning and Data Mining
share announcement

Symmetry and Asymmetry in Machine Learning and Data Mining

A special issue of Symmetry (ISSN 2073-8994). This special issue belongs to the section "Computer".

Deadline for manuscript submissions: 31 December 2026 | Viewed by 1396

Special Issue Editors

Dr. Jantima Polpinij

E-Mail Website
Guest Editor
Faculty of Informatics, Mahasarakham University, Mahasarakham 44150, Thailand
Interests: NLP; text mining; data mining; sentiment analysis; information extraction
Dr. Olarik Surinta

E-Mail Website
Guest Editor
Multi-Agent Intelligent Simulation Laboratory (MISL) Research Unit, Department of Information Technology, Faculty of Informatics, Mahasarakham University, Mahasarakham 44150, Thailand
Interests: artificial intelligence; machine learning; deep learning; pattern recognition; convolutional neural network; feature extraction
Special Issues, Collections and Topics in MDPI journals
Dr. Manasawee Kaenampornpan

E-Mail Website
Guest Editor
Department of Computer Engineering, Faculty of Engineering, Khon Kaen University, Khon Kaen 40002, Thailand
Interests: HCI; mobile and ubiquitous computing; context awareness; social media and digital marketing; software engineering; social listening; computer system design and analysis

Special Issue Information

Dear Colleagues,

Symmetry and asymmetry are fundamental principles in machine learning and data mining that govern how models capture and utilize structural properties of data. Symmetry refers to invariance or equivariance under transformations such as permutation, translation, or rotation, allowing learning algorithms to generalize by exploiting consistent and shared patterns. In contrast, asymmetry represents directional, imbalanced, or non-reciprocal relationships that frequently arise in real-world data, including causal dependencies, hierarchical structures, skewed class distributions, and asymmetric similarity relationships.

Rather than being merely theoretical concepts, symmetry and asymmetry have become central design considerations in modern learning systems. Recent studies show that explicitly incorporating these properties can enhance representation learning, robustness, and model interpretability. Symmetry-aware approaches, such as invariant and equivariant neural architectures, have demonstrated strong performance across structured data domains, while asymmetry-aware methods—including asymmetric loss functions, directed graph learning, imbalance-aware modeling, and asymmetric distance measures—offer effective solutions for handling complex, heterogeneous, and realistic data distributions.

This Special Issue aims to bring together theoretical insights and practical advances that leverage symmetry and asymmetry in machine learning and data mining, with a particular emphasis on data analytics, natural language processing, text mining, data science, big data analytics, and related fields. Topics of interest include symmetry- and asymmetry-aware representation learning, graph and relational data mining, domain adaptation, multimodal learning, and large-scale data analysis. Through the integration of methodological innovations and real-world applications, this Special Issue seeks to advance a deeper understanding of symmetry- and asymmetry-driven learning in intelligent data-driven systems.

Dr. Jantima Polpinij
Dr. Olarik Surinta
Dr. Manasawee Kaenampornpan
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. Symmetry 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 2400 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

  • symmetry and asymmetry in machine learning
  • invariant and equivariant learning
  • asymmetric modeling
  • graph and relational learning
  • data mining and data analytics
  • natural language processing and text mining
  • imbalanced and heterogeneous data
  • domain adaptation
  • big data analytics

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.

Published Papers (2 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

25 pages, 3630 KB  
Article
Modality-Specific Sparse Autoencoders for Efficient Multimodal ICU Alignment: A Symmetry–Asymmetry Learning Framework
by Hashim Ali and Muhammad Tahir Akhtar
Symmetry 2026, 18(4), 677; https://doi.org/10.3390/sym18040677 - 18 Apr 2026
Viewed by 297
Abstract
Intensive care units (ICUs) generate heterogeneous data streams, including structured electronic health records, physiological time series, and medical imaging, that describe the same patient state through different observational forms. Effective multimodal learning in this setting requires a principled balance between representation-level symmetry and [...] Read more.
Intensive care units (ICUs) generate heterogeneous data streams, including structured electronic health records, physiological time series, and medical imaging, that describe the same patient state through different observational forms. Effective multimodal learning in this setting requires a principled balance between representation-level symmetry and architectural asymmetry. Clinically corresponding patient states should exhibit cross-modal representational symmetry, whereas each modality retains intrinsic asymmetry in dimensionality, temporal resolution, noise characteristics, and missingness. This study proposes a modality-specific sparse autoencoder framework for efficient multimodal ICU representation learning under this symmetry–asymmetry principle. Separate sparse encoders are assigned to each modality to preserve the modality-dependent structure while suppressing redundant latent activity through adaptive gating. Representation-level symmetry is encouraged through a sparsity-aware contrastive objective that aligns paired latent embeddings across modalities only on active informative dimensions. To further model inter-patient dependencies, the framework incorporates a graph neural network (GNN) whose message-passing operations respect modality-specific sparsity patterns. Experimental results indicate that the proposed framework improves predictive performance and computational efficiency relative to conventional multimodal baselines, while also exhibiting stronger robustness under missing-modality conditions and more selective latent representations. Overall, the method provides an effective and clinically relevant multimodal learning strategy for ICU decision support while offering a measurable symmetry-aware and asymmetry-preserving formulation for heterogeneous medical data. Full article
(This article belongs to the Special Issue Symmetry and Asymmetry in Machine Learning and Data Mining)
►▼ Show Figures

Figure 1

22 pages, 341 KB  
Article
Symmetry- and Asymmetry-Aware Domain Adaptation for Cross-Domain Sentiment Analysis
by Chumsak Sibunruang, Jantima Polpinij, Manasawee Kaenampornpan, Thananchai Khamket, Jaturong Som-ard, Anirut Chottanom, Jatuphum Juanchaiyaphum, Vuttichai Vichianchai and Bancha Luaphol
Symmetry 2026, 18(2), 357; https://doi.org/10.3390/sym18020357 - 14 Feb 2026
Viewed by 708
Abstract
Cross-domain sentiment analysis remains challenging due to distributional shifts and heterogeneous sentiment expressions across platforms. Existing domain adaptation approaches primarily focus on enforcing domain-invariant representations. However, such symmetry-preserving strategies often overlook directional and expression-level asymmetries. These asymmetries naturally arise in real-world sentiment data, [...] Read more.
Cross-domain sentiment analysis remains challenging due to distributional shifts and heterogeneous sentiment expressions across platforms. Existing domain adaptation approaches primarily focus on enforcing domain-invariant representations. However, such symmetry-preserving strategies often overlook directional and expression-level asymmetries. These asymmetries naturally arise in real-world sentiment data, particularly for context-inferred sentiment expressions. In this work, we propose a novel symmetry- and asymmetry-aware domain adaptation framework for cross-domain sentiment classification. The framework models symmetry through explicit multi-source distribution alignment, which captures transferable sentiment knowledge across domains. Additionally, aspect-level structural supervision organizes representations according to shared linguistic aspects. To address asymmetry, a directional divergence regularization is introduced. This component models expression-level and directional discrepancies between source and target domains. Importantly, the framework operates without requiring target-domain annotations. Experiments are conducted under a multi-source unsupervised domain adaptation setting using sentence-level hotel review datasets collected from multiple online platforms. Empirical results demonstrate strong performance for the proposed framework. It achieves an average Accuracy of 82.0% and Macro-F1 of 80.6%. The framework consistently and statistically significantly outperforms source-only, multi-source, and transformer-based adversarial adaptation baselines across all evaluated target domains (p < 0.05). Additional analyses confirm improved robustness to implicit sentiment expressions and platform-induced asymmetries. These findings highlight the importance of jointly modeling symmetry and asymmetry for robust cross-domain sentiment adaptation and provide a unified and deployable solution for sentiment analysis under realistic platform shifts. Full article
(This article belongs to the Special Issue Symmetry and Asymmetry in Machine Learning and Data Mining)
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-2
Back to TopTop