Neural architecture search via reference point based multi‐objective evolutionary algorithm
作者：
Highlights：
• We propose RNSGA-Net for neural architecture search, which balances the conflict objectives and considers the preference of decision-makers.
• We augment an extra bit value of the original encoding to represent two types of residual block and one type of dense block for residual connection and dense connection.
• Experiment results on the CIFAR-10 dataset demonstrate that RNSGA-Net can improve NSGA-Net in terms of the more structured representation space and the preference of decision-makers.
摘要
•We propose RNSGA-Net for neural architecture search, which balances the conflict objectives and considers the preference of decision-makers.•We augment an extra bit value of the original encoding to represent two types of residual block and one type of dense block for residual connection and dense connection.•Experiment results on the CIFAR-10 dataset demonstrate that RNSGA-Net can improve NSGA-Net in terms of the more structured representation space and the preference of decision-makers.
论文关键词：Neural architecture search,Multi-objective evolutionary algorithm,The image classification
论文评审过程：Received 12 May 2022, Revised 12 July 2022, Accepted 7 August 2022, Available online 8 August 2022, Version of Record 26 August 2022.
论文官网地址：https://doi.org/10.1016/j.patcog.2022.108962
