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/Asymmetry in Evolutionary Computation and Machine Learning
share announcement

Symmetry/Asymmetry in Evolutionary Computation and Machine Learning

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

Deadline for manuscript submissions: 31 March 2026 | Viewed by 2185

Special Issue Editors

Dr. Shuwei Zhu

E-Mail Website1 Website2
Guest Editor
School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi 214122, China
Interests: evolutionary computation; machine learning; clustering algorithm; pattern recognition
Special Issues, Collections and Topics in MDPI journals
Dr. Leilei Cao

E-Mail Website
Guest Editor
Innovation Center of Yangtze River Delta, Zhejiang University, Jiashan 314100, China
Interests: evolutionary computation; machine learning; computer vision; path planning
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Evolutionary computation (EC), a family of algorithms inspired by biological evolution for global optimization, has been developed for a few decades. Potential applications are wide-ranging and include problems from combinatorial optimization, multi-objective optimization, and numerical optimization in diverse domains, such as engineering, biology, medicine, robotics, etc. Machine learning (ML) is one of the most engaging research and application areas within computer science today. Its ability to find patterns, clusters, and hidden knowledge from data has allowed us to understand, model, and predict the behaviors of complex systems.

Nowadays, symmetry and asymmetry play important roles in various aspects of EC and ML. These concepts can be applied to algorithm design, problem representation, and solution optimization. Usually, the concept of a fitness landscape in EC assumes a certain level of symmetry where similar solutions have similar fitness values. This symmetry can help in navigating the search space more efficiently. Also, symmetry/asymmetry is critical in ML, particularly in the design of algorithms and the interpretation of data. For example, the structure of many neural networks assumes symmetry in the weights and biases.

This Special Issue aims to explore the current impact, advances, and applications of symmetry/asymmetry in EC and ML. For either EC or ML, understanding and exploiting symmetry can lead to more efficient algorithms, while recognizing and addressing asymmetry is crucial for the robustness and generalization of algorithms or models. Researchers and practitioners must be aware of these properties when designing algorithms and interpreting results. Moreover, it is interesting to combine ML and EMO ideas in a single coherent framework. EC is very helpful to solve complex ML problems, e.g., when the fitness function of the ML model has many local extremes that can trap sequential methods. Meanwhile, ML methods can be used to analyze EC population data to better understand the problem structure, to understand what makes the solutions optimal, and to create new and often superior solutions.

We invite submissions on recent advances in the theory and applications of evolutionary computation and machine learning that explore the role of symmetry and asymmetry.

Dr. Shuwei Zhu
Dr. Leilei Cao
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. 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

  • evolutionary computation
  • machine learning
  • swarm intelligence
  • bio-inspired optimization
  • pattern classification and clustering analysis
  • symmetry in evolutionary single-objective and multi-objective optimization
  • symmetry in regularization techniques
  • symmetry in data augmentation
  • symmetry in neural networks and deep learning
  • symmetry and asymmetric similarity measures

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 (3 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

23 pages, 1889 KB  
Article
Adaptive Switching Surrogate Model for Evolutionary Multi-Objective Community Detection Algorithm
by Nan Sun, Siying Lv, Xiaoying Xiang, Shuwei Zhu, Hengyang Lu and Wei Fang
Symmetry 2025, 17(8), 1213; https://doi.org/10.3390/sym17081213 - 31 Jul 2025
Viewed by 320
Abstract
Community detection is widely recognized as a crucial area of research in network science. In recent years, multi-objective evolutionary algorithms (MOEAs) have been extensively employed in community detection tasks. Continuous coding is able to transform the discrete problem into a continuous one. However, [...] Read more.
Community detection is widely recognized as a crucial area of research in network science. In recent years, multi-objective evolutionary algorithms (MOEAs) have been extensively employed in community detection tasks. Continuous coding is able to transform the discrete problem into a continuous one. However, conventional continuous coding methodologies frequently disregard the relationships between node structures, resulting in low-quality encoded populations that subsequently diminish community detection performance. Furthermore, continuous coding needs to be decoded into to label-based coding during the optimization process to compute objective functions. To alleviate this, we design the surrogate model adaptive switching strategy that selects the optimal surrogate model for the task. Subsequently, the surrogate-assisted evolutionary multi-objective community detection algorithm with core node learning is proposed. The core node learning method is employed to enhance the connection between nodes in augmented sequential coding, which helps initialize the population using the node similarity matrix. The core nodes of the network are subsequently identified based on node weights, which can be utilized to construct a surrogate model between the continuous coding and the objective function. The surrogate model is updated during the optimization process, which effectively improves both the accuracy and efficiency of community detection tasks. Experimental results obtained from synthetic and real-world networks demonstrate that the proposed algorithm exhibits superior performance compared to seven community detection algorithms. Full article
(This article belongs to the Special Issue Symmetry/Asymmetry in Evolutionary Computation and Machine Learning)
►▼ Show Figures

Figure 1

21 pages, 5385 KB  
Article
GGD-YOLOv8n: A Lightweight Architecture for Edge-Computing-Optimized Allergenic Pollen Recognition with Cross-Scale Feature Fusion
by Tianrui Zhang, Xiaoqiang Jia, Ying Cui and Hanyu Zhang
Symmetry 2025, 17(6), 849; https://doi.org/10.3390/sym17060849 - 29 May 2025
Cited by 1 | Viewed by 593
Abstract
Pollen allergy has emerged as a critical global health challenge. Proactive pollen monitoring is imperative for safeguarding susceptible populations through timely preventive interventions. Current manual detection methods suffer from inherent limitations: notably, suboptimal accuracy and delayed response times, which hinder effective allergy management. [...] Read more.
Pollen allergy has emerged as a critical global health challenge. Proactive pollen monitoring is imperative for safeguarding susceptible populations through timely preventive interventions. Current manual detection methods suffer from inherent limitations: notably, suboptimal accuracy and delayed response times, which hinder effective allergy management. Therefore, we present an automated pollen concentration detection system integrated with a novel GGD-YOLOv8n model (Ghost-generalized-FPN-DualConv-YOLOv8), which was specifically designed for allergenic pollen species identification. The methodological advancements comprise three components: (1) combining the C2f convolution in Backbone with the G-Ghost module, this module generates features through half-convolution operations and half-symmetric linear operations, enhancing the extraction and expression capabilities of detailed feature information. (2) The conventional neck network is replaced with a GFPN architecture, facilitating cross-scale feature aggregation and refinement. (3) Standard convolutional layers are substituted with DualConv, thereby reducing model complexity by 22.6% (parameters) and 22% GFLOPs (computational load) while maintaining competitive detection accuracy. This systematic optimization enables efficient deployment on edge computing platforms with stringent resource constraints. The experimental validation substantiates that the proposed methodology outperforms the baseline YOLOv8n model, attaining a 5.4% increase in classification accuracy accompanied by a 4.7% enhancement in mAP@50 metrics. When implemented on Jetson Nano embedded platforms, the system demonstrates computational efficiency with an inference latency of 364.9 ms per image frame, equating to a 22.5% reduction in processing time compared to conventional implementations. The empirical results conclusively validate the dual superiority in detecting precision and operational efficacy when executing microscopic pollen image analysis on resource-constrained edge computing devices; they establish a feasible algorithm framework for automated pollen concentration monitoring systems. Full article
(This article belongs to the Special Issue Symmetry/Asymmetry in Evolutionary Computation and Machine Learning)
►▼ Show Figures

Figure 1

16 pages, 1003 KB  
Article
Cross-Session Graph and Hypergraph Co-Guided Session-Based Recommendation
by Pingrong Li and Huifang Ma
Symmetry 2025, 17(3), 389; https://doi.org/10.3390/sym17030389 - 4 Mar 2025
Viewed by 854
Abstract
Session-based recommendation (SBR) aims to predict a user’s next item of interest by analyzing their anonymous browsing patterns. While previous studies have demonstrated considerable efficacy, they may fall short when confronted with exceedingly sparse interaction data. This paper presents a novel approach, cross-session [...] Read more.
Session-based recommendation (SBR) aims to predict a user’s next item of interest by analyzing their anonymous browsing patterns. While previous studies have demonstrated considerable efficacy, they may fall short when confronted with exceedingly sparse interaction data. This paper presents a novel approach, cross-session graph and hypergraph co-guided session-based recommendation (CGH-SBR), which adeptly forecasts subsequent items while upholding efficiency and precision. First, we construct a directed graph that captures sequential dependencies by modeling cross-session item transitions, alongside building a hypergraph that encapsulates higher-order relationships between items within sessions. Subsequently, we employ two distinct graph neural networks (GNNs) to learn item representations on these two graphs separately. Further, we innovate by integrating a symmetry-aware co-guided learning framework. This framework promotes the integration of diverse perspectives and facilitates mutual learning, leveraging the data’s symmetric properties to enhance the model’s pattern recognition capabilities. Comprehensive experimentation conducted on two public datasets showcases the outstanding performance and potential of the recommendation system presented by CGH-SBR. Full article
(This article belongs to the Special Issue Symmetry/Asymmetry in Evolutionary Computation and Machine Learning)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-3
Back to TopTop