Metaheuristic-based ensemble learning: an extensive review of methods and applications

• Published in: Neural computing & applications Vol. 36; no. 29; pp. 17931 - 17959
• Main Authors: Rezk, Sahar Saeed, Selim, Kamal Samy
• Format: Journal Article
• Language: English
• Published: London Springer London 01-10-2024; Springer Nature B.V
• Subjects: Algorithms; Artificial Intelligence; Cluster analysis; Computational Biology/Bioinformatics; Computational Science and Engineering; Computer Science; Computing time; Data Mining and Knowledge Discovery; Ensemble learning; Heuristic methods; Image Processing and Computer Vision; Machine learning; Mathematical programming; Memory tasks; Optimization; Parameter identification; Parameter robustness; Probability and Statistics in Computer Science; Problem solving; Review; Robustness; Software; Taxonomy; Trends; Ensemble pruning; Swam intelligence; Hybrid learning; Evolutionary computation; Optimization metaheuristics
• ISSN: 0941-0643; 1433-3058
• DOI: 10.1007/s00521-024-10203-4

Ensemble learning has become a cornerstone in various classification and regression tasks, leveraging its robust learning capacity across disciplines. However, the computational time and memory constraints associated with almost all-learners-based ensembles necessitate efficient approaches. Ensemble pruning, a crucial step, involves selecting a subset of base learners to address these limitations. This study underscores the significance of optimization-based methods in ensemble pruning, with a specific focus on metaheuristics as high-level problem-solving techniques. It reviews the intersection of ensemble learning and metaheuristics, specifically in the context of selective ensembles, marking a unique contribution in this direction of research. Through categorizing metaheuristic-based selective ensembles, identifying their frequently used algorithms and software programs, and highlighting their uses across diverse application domains, this research serves as a comprehensive resource for researchers and offers insights into recent developments and applications. Also, by addressing pivotal research gaps, the study identifies exploring selective ensemble techniques for cluster analysis, investigating cutting-edge metaheuristics and hybrid multi-class models, and optimizing ensemble size as well as hyper-parameters within metaheuristic iterations as prospective research directions. These directions offer a robust roadmap for advancing the understanding and application of metaheuristic-based selective ensembles.