Topics of interest include, but are not limited to:

1) Potential multi-objective machine learning tasks, including:

• Multi-objective optimization for feature selection, feature construction, feature extraction;
• Multi-objective optimization for classification, regression, clustering, semi-supervised learning, and reinforcement learning;
• Multi-objective neural architecture search;
• Multi-objective generation of ensembles;
• Multi-objective optimization for imbalance learning;
• Multi-objective optimization for transfer learning and domain adaptation;
• Multiobjective hyperparameter optimization;
• Multi-objective optimization for explainable machine learning or interpretable AI;
• Multi-objective optimization for AutoML;
• Applications in multi-objective machine learning.

2) Developing evolutionary multi-objective optimization paradigms for machine learning, including:

• Solution representation;
• Fitness function construction;
• Mating selection and environmental selection ;
• Multi-objective search algorithms (e.g., genetic algorithms, genetic programming, evolutionary strategies, evolutionary programming, particle swarm optimization, ant colony optimization, differential evolution);
• Performance measure;
• Theoretical studies;
• Decision-making in machine learning.