Abstract
Evolutionary Neural Architecture Search (ENAS) can automatically design the architectures of Deep Neural Networks (DNNs) using evolutionary computation algorithms. It has been greatly witnessed by DNN researchers owing to the promising performance of automatically designing the satisfied DNN architectures. However, most ENAS algorithms require intensive computational resource which is not necessarily available to each of the users interested. Performance predictors are a type of regression models, can assist to accomplish the search without much computational resource. Despite various performance predictors have been designed, they employ the same training protocol to build the regression models: 1) sampling a set of DNNs with performance as the training dataset, 2) training the model with the mean square error criterion, and 3) predicting the performance of DNNs newly generated during the ENAS. In this paper, we point out that the three steps constituting the training protocol are not reasonable through intuitive and illustrative examples. Further, we propose a new training protocol to address the issues, consisting of designing a pair-wise ranking indicator to construct the training target, proposing to use the logistic regression to fit the training samples, and developing a differential method to building the training instances. To verify the effectiveness of the proposed training protocol, four widely used regression models in the field of machine learning have been chosen to perform the comparisons on two benchmark datasets. The experimental results of all the comparisons demonstrate that the proposed protocol can significantly improve the performance prediction accuracy against the traditional training protocol.
Abstract (translated)
URL
https://arxiv.org/abs/2008.13187
