# An Efficient Evolutionary Deep Learning Framework Based on Multi-source Transfer Learning to Evolve Deep Convolutional Neural Networks

arXiv: https://arxiv.org/abs/2212.03942 · HTML: https://mlsanity.com/paper/2212.03942/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 47 references that are in the map.
- First posted on arXiv 7 Dec 2022.

## Builds on (most cited first, 28 of 28)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Learning Transferable Architectures for Scalable Image Recognition](https://mlsanity.com/paper/1707.07012/) (2017)
- [Deep Networks with Stochastic Depth](https://mlsanity.com/paper/1603.09382/) (2016)
- [Regularized Evolution for Image Classifier Architecture Search](https://mlsanity.com/paper/1802.01548/) (2018)
- [Network In Network](https://mlsanity.com/paper/1312.4400/) (2013)
- [Deeply-Supervised Nets](https://mlsanity.com/paper/1409.5185/) (2014)
- [Large-Scale Evolution of Image Classifiers](https://mlsanity.com/paper/1703.01041/) (2017)
- [FractalNet: Ultra-Deep Neural Networks without Residuals](https://mlsanity.com/paper/1605.07648/) (2016)
- [SMASH: One-Shot Model Architecture Search through HyperNetworks](https://mlsanity.com/paper/1708.05344/) (2017)
- [Hierarchical Representations for Efficient Architecture Search](https://mlsanity.com/paper/1711.00436/) (2017)
- [Deep Pyramidal Residual Networks](https://mlsanity.com/paper/1610.02915/) (2016)
- [Genetic CNN](https://mlsanity.com/paper/1703.01513/) (2017)
- [Evolving Deep Neural Networks](https://mlsanity.com/paper/1703.00548/) (2017)
- [NSGANetV2: Evolutionary Multi-Objective Surrogate-Assisted Neural Architecture Search](https://mlsanity.com/paper/2007.10396/) (2020)
- [A Genetic Programming Approach to Designing Convolutional Neural Network Architectures](https://mlsanity.com/paper/1704.00764/) (2017)
- [Simple And Efficient Architecture Search for Convolutional Neural Networks](https://mlsanity.com/paper/1711.04528/) (2017)
- [Evolving Deep Neural Networks by Multi-objective Particle Swarm Optimization for Image Classification](https://mlsanity.com/paper/1904.09035/) (2019)
- [Particle Swarm Optimisation for Evolving Deep Neural Networks for Image Classification by Evolving and Stacking Transferable Blocks](https://mlsanity.com/paper/1907.12659/) (2019)
- [Evolving Deep Convolutional Neural Networks by Variable-length Particle Swarm Optimization for Image Classification](https://mlsanity.com/paper/1803.06492/) (2018)
- [Surrogate-assisted Particle Swarm Optimisation for Evolving Variable-length Transferable Blocks for Image Classification](https://mlsanity.com/paper/2007.01556/) (2020)
- [A Hybrid Differential Evolution Approach to Designing Deep Convolutional Neural Networks for Image Classification](https://mlsanity.com/paper/1808.06661/) (2018)
- [EIGEN: Ecologically-Inspired GENetic Approach for Neural Network Structure Searching from Scratch](https://mlsanity.com/paper/1806.01940/) (2018)
- [A Hybrid GA-PSO Method for Evolving Architecture and Short Connections of Deep Convolutional Neural Networks](https://mlsanity.com/paper/1903.03893/) (2019)

## Abstract (arXiv)

Convolutional neural networks (CNNs) have constantly achieved better performance over years by introducing more complex topology, and enlarging the capacity towards deeper and wider CNNs. This makes the manual design of CNNs extremely difficult, so the automated design of CNNs has come into the research spotlight, which has obtained CNNs that outperform manually-designed CNNs. However, the computational cost is still the bottleneck of automatically designing CNNs. In this paper, inspired by transfer learning, a new evolutionary computation based framework is proposed to efficiently evolve CNNs without compromising the classification accuracy. The proposed framework leverages multi-source domains, which are smaller datasets than the target domain datasets, to evolve a generalised CNN block only once. And then, a new stacking method is proposed to both widen and deepen the evolved block, and a grid search method is proposed to find optimal stacking solutions. The experimental results show the proposed method acquires good CNNs faster than 15 peer competitors within less than 40 GPU-hours. Regarding the classification accuracy, the proposed method gains its strong competitiveness against the peer competitors, which achieves the best error rates of 3.46%, 18.36% and 1.76% for the CIFAR-10, CIFAR-100 and SVHN datasets, respectively.