Evolutionary Transfer Optimization - A New Frontier in Evolutionary Computation Research

Contribution

Defines evolutionary transfer optimization as a field and gives it a shared agenda.

Abstract

Most real-world optimization problems are not isolated: solving one gives you experience that should accelerate solving the next. This article articulates a vision for evolutionary transfer optimization as a first-class research frontier, in which search algorithms explicitly carry knowledge — about solutions, landscapes, hyperparameters, and problem structure — across related tasks. The authors survey existing efforts, identify the open theoretical and algorithmic questions, and propose a unifying taxonomy that has since guided the design of dozens of new algorithms for dynamic, multi-task, and expensive optimization scenarios.

Why This Paper Matters

If your research touches transfer learning, surrogate modeling, multi-task optimization, or expensive black-box problems, this IEEE CIM article is the canonical starting point and the source most authors cite to motivate their work.

BibTeX

@article{tan2021evolutionary,
  title={Evolutionary Transfer Optimization - A New Frontier in Evolutionary Computation Research},
  author={Tan, Kay Chen and Feng, Liang and Jiang, Min},
  journal={IEEE Computational Intelligence Magazine},
  volume={16},
  number={1},
  pages={22--33},
  year={2021},
  publisher={IEEE},
}