A Survey on Computational Intelligence-based Transfer Learning

  title={A Survey on Computational Intelligence-based Transfer Learning},
  author={Mohamad Zamini and Eunjin Kim},
The goal of transfer learning (TL) is providing a framework for exploiting acquired knowledge from source to target data. Transfer learning approaches compared to traditional machine learning approaches are capable of modeling better data patterns from the current domain. However, vanilla TL needs performance improvements by using computational intelligencebased TL. This paper studies computational intelligence-based transfer learning techniques and categorizes them into neural network-based… 

Figures from this paper



A particle swarm optimization based feature selection approach to transfer learning in classification

This work proposes a new feature-based transfer learning method using particle swarm optimization (PSO), where a new fitness function is developed to guide PSO to automatically select a number of original features and shift source and target domains to be closer.

Transfer Learning-Based Dynamic Multiobjective Optimization Algorithms

This approach exploits the transfer learning technique as a tool to generate an effective initial population pool via reusing past experience to speed up the evolutionary process, and at the same time any population-based multiobjective algorithms can benefit from this integration without any extensive modifications.

A particle swarm optimization-based feature selection for unsupervised transfer learning

This paper proposes a novel feature selection-based transfer learning approach using particle swarm optimization (PSO) for unsupervised transfer learning (FSUTL-PSO), which has shown significant improvement over the existing transfer or non-transfer learning methods.

Semi-Supervised Transfer Learning with Genetic Algorithm Tuned Transformation and Novel Label Transfer Mechanism

A new optimized method is proposed in this work to transform the observation from source domain along with a new label transfer mechanism that outperforms any classifier trained only with source or target domain data.

Particle swarm optimization based parameter selection technique for unsupervised discriminant analysis in transfer learning framework

A Particle Swarm Optimization based Parameter Selection Approach for Unsupervised Discriminant Analysis (UDATL-PSO) in transfer learning framework is proposed, which has a significant influence on state-of-the-art methods.

Transfer learning for gaussian process assisted evolutionary bi-objective optimization for objectives with different evaluation times

A surrogate assisted evolutionary algorithm along with a parameter-based transfer learning (T-SAEA) is proposed in this work and demonstrates that the proposed algorithm outperforms the compared algorithms on the bi-objective optimization problems whose objectives have a large difference in computational complexities.

Genetic Programming for Instance Transfer Learning in Symbolic Regression

A new instance weighting framework for transfer learning in genetic programming-based symbolic regression which can evolve regression models which not only achieve notably better cross-domain generalization performance in stability but also reduce the trend of overfitting effectively.

Differential evolution for instance based transfer learning in genetic programming for symbolic regression

This work proposes a new instance weighting framework for genetic programming (GP) based symbolic regression for transfer learning to use differential evolution to search for optimal weights during the evolutionary process of GP.