Pareto-wise Ranking Classifier for Multi-objective Evolutionary Neural Architecture Search

arXiv:2109.07582v2 Announce Type: replace
Abstract: In the deployment of deep neural models, how to effectively and automatically find feasible deep models under diverse design objectives is fundamental. Most existing neural architecture search (NAS) methods utilize surrogates to predict the detailed performance (e.g., accuracy and model size) of a candidate architecture during the search, which however is complicated and inefficient. In contrast, we aim to learn an efficient Pareto classifier to simplify the search process of NAS by transforming the complex …

abstract accuracy architecture arxiv classifier cs.lg deployment design diverse multi-objective nas neural architecture search pareto performance ranking search type wise