# Learning and Sharing: A Multitask Genetic Programming Approach to Image Feature Learning

arXiv: https://arxiv.org/abs/2012.09444 · HTML: https://mlsanity.com/paper/2012.09444/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Dec 2020.

## Built on by (most cited first, 7 of 7)

- [Half a Dozen Real-World Applications of Evolutionary Multitasking, and More](https://mlsanity.com/paper/2109.13101/) (2021)
- [A Survey on Evolutionary Computation for Computer Vision and Image Analysis: Past, Present, and Future Trends](https://mlsanity.com/paper/2209.06399/) (2022)
- [Genetic Programming-Based Evolutionary Deep Learning for Data-Efficient Image Classification](https://mlsanity.com/paper/2209.13233/) (2022)
- [A Novel Knowledge-Based Genetic Algorithm for Robot Path Planning in Complex Environments](https://mlsanity.com/paper/2209.01482/) (2022)
- [Interactive LLM-assisted Curriculum Learning for Multi-Task Evolutionary Policy Search](https://mlsanity.com/paper/2602.10891/) (2026)
- [Evolutionary Multitasking with Solution Space Cutting for Point Cloud Registration](https://mlsanity.com/paper/2212.05679/) (2022)
- [EvoTSC: Evolving Feature Learning Models for Time Series Classification via Genetic Programming](https://mlsanity.com/paper/2604.25499/) (2026)

## Abstract (arXiv)

Using evolutionary computation algorithms to solve multiple tasks with knowledge sharing is a promising approach. Image feature learning can be considered as a multitask problem because different tasks may have a similar feature space. Genetic programming (GP) has been successfully applied to image feature learning for classification. However, most of the existing GP methods solve one task, independently, using sufficient training data. No multitask GP method has been developed for image feature learning. Therefore, this paper develops a multitask GP approach to image feature learning for classification with limited training data. Owing to the flexible representation of GP, a new knowledge sharing mechanism based on a new individual representation is developed to allow GP to automatically learn what to share across two tasks and to improve its learning performance. The shared knowledge is encoded as a common tree, which can represent the common/general features of two tasks. With the new individual representation, each task is solved using the features extracted from a common tree and a task-specific tree representing task-specific features. To learn the best common and task-specific trees, a new evolutionary process and new fitness functions are developed. The performance of the proposed approach is examined on six multitask problems of 12 image classification datasets with limited training data and compared with three GP and 14 non-GP-based competitive methods. Experimental results show that the new approach outperforms these compared methods in almost all the comparisons. Further analysis reveals that the new approach learns simple yet effective common trees with high effectiveness and transferability.