Symmetry in Intelligent Algorithms: 2nd Edition
A special issue of Symmetry (ISSN 2073-8994). This special issue belongs to the section "Computer".
Deadline for manuscript submissions: 30 September 2026 | Viewed by 163
Special Issue Editors
2. Yunnan Key Laboratory of Software Engineering, Yunnan University, Kunming 650504, China
Interests: evolutionary algorithm; cooperative coevolution; differential evolution
Special Issues, Collections and Topics in MDPI journals
Interests: swarm intelligence; evolutionary computation; evolutionary game; machine learning
Special Issues, Collections and Topics in MDPI journals
Special Issue Information
Dear Colleagues,
Building upon the foundational topics established in the first volume, we are pleased to announce the second volume of this Special Issue on “Symmetry in Intelligent Algorithms.” This Special Issue continues to explore the pivotal role of symmetry across the full spectrum of intelligent computation, with a particular emphasis on extending these principles to the rapidly advancing fields of machine learning (ML) and large language models (LLMs).
We invite contributions that investigate how symmetry—whether structural, behavioral, or operational—can be leveraged to enhance the design, efficiency, robustness, and fairness of next-generation intelligent algorithms. This Special Issue aims to bridge traditional swarm intelligence and evolutionary computation with modern ML and LLM paradigms, fostering a holistic understanding of symmetry’s unifying potential.
Topics of interest include (but are not limited to) the following:
- Fundamentals and Theoretical Advances
- Theoretical foundations of symmetry in ML optimization and LLM training dynamics;
- Symmetry principles in the convergence analysis of neural networks and evolutionary algorithms;
- Hybrid theoretical models integrating swarm intelligence with deep learning architectures.
- Algorithm Design and Optimization with Symmetry
- Novel swarm intelligence algorithms (e.g., Ant Colony Optimization, Particle Swarm Optimization, Artificial Bee Colony);
- Innovative evolutionary computation techniques (e.g., Genetic Algorithms, Genetic Programming, Differential Evolution);
- Symmetry-aware neural architecture design (e.g., group-equivariant networks, symmetric attention mechanisms in Transformers);
- Evolutionary algorithms for automated design and optimization of ML/LLM architectures and hyperparameters;
- Symmetry in training algorithms: gradient descent variants, regularization, and distributed training for large models;
- Symmetry-breaking techniques to escape local optima in deep learning loss landscapes.
- Applications in Engineering, Industry, and AI Systems
- Symmetry in LLM Applications: prompt engineering, reasoning, text generation, and code synthesis;
- ML/LLM-powered optimization in robotics, logistics, smart grids, and telecommunications;
- Symmetry principles in multimodal AI systems (vision–language–audio);
- Real-world applications of hybrid systems (e.g., swarm intelligence for LLM agent coordination).
- Symmetry in Data, Models, and Intelligence
- Data and Feature Symmetry: symmetric data augmentation, invariant feature learning, and fairness in datasets for ML/LLMs;
- Behavioral and Structural Symmetry: symmetry in multi-agent reinforcement learning, swarm behavior emergent from LLM-based agents, and symmetrical communication protocols in decentralized AI;
- Model Interpretability and Robustness: using symmetry to explain model decisions, verify robustness, and detect adversarial vulnerabilities in ML/LLMs.
Dr. Hongwei Kang
Dr. Xinping Sun
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
- intelligent algorithms
- swarm intelligence
- evolutionary computation
- machine learning
- deep learning
- large language models (LLMs)
- transformers
- neural architecture design
- optimization
- algorithmic fairness
- hybrid models
- multimodal AI
- explainable AI
- robustness
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.
