Evolutionary Machine Learning: Methods, Theory, and Applications
A special issue of Algorithms (ISSN 1999-4893). This special issue belongs to the section "Evolutionary Algorithms and Machine Learning".
Deadline for manuscript submissions: 31 October 2026 | Viewed by 212
Special Issue Editors
Interests: evolutionary computation; particle swarm optimization; machine learning; big data analysis
Special Issues, Collections and Topics in MDPI journals
Interests: optimization; big data; multi-criteria decision making; metaheuristics; semantic web
Interests: multi-objective optimization; metaheuristics; parallel computing; optimization software frameworks
Special Issues, Collections and Topics in MDPI journals
Special Issue Information
Dear Colleagues,
Evolutionary machine learning (EML) is a rapidly expanding research area at the intersection of evolutionary computation, optimization, and machine learning. By integrating evolutionary algorithms, genetic programming, and other population-based and bio-inspired techniques into learning systems, EML provides powerful mechanisms for model design, adaptation, and optimization in complex, high-dimensional, and non-convex problem settings.
Evolutionary approaches have been successfully applied to varied machine learning tasks, including model structure optimization, feature selection and construction, hyperparameter tuning, ensemble learning, and neural architecture search. In addition, evolutionary and population-based optimization methods play a key enabling role in several emerging learning paradigms, including automated machine learning (AutoML), federated learning, and transfer learning, where adaptive, distributed, and data-efficient optimization is essential.
Beyond using evolutionary methods to optimize machine learning systems, an increasingly important research focus is the complementary use of machine learning techniques to monitor, model, and improve the behaviour of evolutionary and population-based algorithms. This includes learning-based algorithm configuration, adaptive operator selection, performance prediction, dynamic parameter control, and data-driven analysis of evolutionary search dynamics.
This Special Issue focuses on theoretical advances, algorithmic developments, and practical applications of evolutionary machine learning. Contributions related to AutoML, federated learning, and transfer learning are welcome when they emphasize evolutionary or population-based optimization components, or when they provide novel insights into the roles of evolutionary methods in automated, distributed, or knowledge transfer-based learning systems. Likewise, contributions on machine learning for evolutionary algorithm analysis, control, and self-adaptation are strongly encouraged.
This Special Issue will bring together high-quality contributions that advance the state of the art in evolutionary machine learning, foster interaction between the evolutionary computation and machine learning communities, and highlight emerging research directions in adaptive, automated, and distributed learning driven by evolutionary principles.
The scope of this Special Issue includes, but is not limited to, the following topics:
- Evolutionary Machine Learning algorithms and frameworks;
- Generative AI for EML;
- AutoML and/or auto-parameter tunning;
- Neural architecture search using evolutionary and population-based methods;
- Multi-objective evolutionary learning;
- Evolutionary ensemble learning;
- Evolutionary deep learning;
- Explainability and interpretability in evolutionary learning systems;
- Evolutionary approaches for federated learning and distributed learning systems;
- Data-driven visualization of evolutionary machine learning;
- Metaheuristic methods for time-series forecasting;
- Adaptive operator selection using machine learning techniques;
- Data-driven analysis of evolutionary search dynamics;
- Real-world applications of evolutionary machine learning (e.g., bioinformatics, healthcare, engineering, smart cities, agriculture and agroecology, industry).
Prof. Dr. José Manuel García-Nieto
Dr. Cristóbal Barba-González
Prof. Dr. Antonio J. Nebro
Dr. Sandro Hurtado
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. Algorithms 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 1800 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
- machine learning
- evolutionary algorithms
- swarm intelligence
- ensemble models
- deep learning
- generative AI
- real-world applications
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.
