# A Surrogate-Assisted Highly Cooperative Coevolutionary Algorithm for Hyperparameter Optimization in Deep Convolutional Neural Network

Source: [A Surrogate-Assisted Highly Cooperative Coevolutionary Algorithm for Hyperparameter Optimization in Deep Convolutional Neural Network](<https://www.sota2.com/research/paper/68fa6ead1e209131cea4159c>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T01:03:50.423Z

Authors: An Chen, Zhigang Ren, Muyi Wang, Hui Chen, Haoxi Leng, Shuai Liu

Published: 2023-02-25T02:50:58.000Z

## Abstract

Convolutional neural networks (CNNs) have gained remarkable success in recent years. However, their performance highly relies on the architecture hyperparameters, and finding proper hyperparameters for a deep CNN is a challenging optimization problem owing to its high-dimensional and computationally expensive characteristics. Given these difficulties, this study proposes a surrogate-assisted highly cooperative hyperparameter optimization (SHCHO) algorithm for chain-styled CNNs. To narrow the large search space, SHCHO first decomposes the whole CNN into several overlapping sub-CNNs in accordance with the overlapping hyperparameter interaction structure and then cooperatively optimizes these hyperparameter subsets. Two cooperation mechanisms are designed during this process. One coordinates all the sub-CNNs to reproduce the information flow in the whole CNN and achieve macro cooperation among them, and the other tackles the overlapping components by simultaneously considering the involved two sub-CNNs and facilitates micro cooperation between them. As a result, a proper hyperparameter configuration can be effectively located for the whole CNN. Besides, SHCHO also employs the well-performing surrogate technique to assist in the hyperparameter optimization of each sub-CNN, thereby greatly reducing the expensive computational cost. Extensive experimental results on two widely-used image classification datasets indicate that SHCHO can significantly improve the performance of CNNs.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2302.12963>)

[PDF](<https://arxiv.org/pdf/2302.12963.pdf>)
