TY  - EJOU
AU  - Khan, Irfan 
AU  - Zhang, Xianchao 
AU  - Ayyasamy, Ramesh Kumar 
AU  - Alhashmi, Saadat M. 
AU  - Rahim, Azizur 

TI  - Enhancing Classification Algorithm Recommendation in Automated Machine Learning: A Meta-Learning Approach Using Multivariate Sparse Group Lasso
T2  - Computer Modeling in Engineering \& Sciences

PY  - 2025
VL  - 142
IS  - 2
SN  - 1526-1506

AB  - The rapid growth of machine learning (ML) across fields has intensified the challenge of selecting the right algorithm for specific tasks, known as the Algorithm Selection Problem (ASP). Traditional trial-and-error methods have become impractical due to their resource demands. Automated Machine Learning (AutoML) systems automate this process, but often neglect the group structures and sparsity in meta-features, leading to inefficiencies in algorithm recommendations for classification tasks. This paper proposes a meta-learning approach using Multivariate Sparse Group Lasso (MSGL) to address these limitations. Our method models both within-group and across-group sparsity among meta-features to manage high-dimensional data and reduce multicollinearity across eight meta-feature groups. The Fast Iterative Shrinkage-Thresholding Algorithm (FISTA) with adaptive restart efficiently solves the non-smooth optimization problem. Empirical validation on 145 classification datasets with 17 classification algorithms shows that our meta-learning method outperforms four state-of-the-art approaches, achieving 77.18% classification accuracy, 86.07% recommendation accuracy and 88.83% normalized discounted cumulative gain.
KW  - Meta-learning; machine learning; automated machine learning; classification; meta-features

DO  - 10.32604/cmes.2025.058566