Cascade Bagging for Accuracy Prediction with Few Training Samples

TL;DR

This paper introduces a novel framework combining data augmentation and cascade bagging ensemble learning to accurately predict neural network performance with limited training samples, reducing computational costs.

Contribution

It proposes a new approach that enables effective accuracy prediction under few training samples using data augmentation and cascade bagging, improving NAS efficiency.

Findings

Effective accuracy prediction with limited data

Validated in CVPR 2021 Lightweight NAS Challenge

Code publicly available for reproducibility

Abstract

Accuracy predictor is trained to predict the validation accuracy of an network from its architecture encoding. It can effectively assist in designing networks and improving Neural Architecture Search(NAS) efficiency. However, a high-performance predictor depends on adequate trainning samples, which requires unaffordable computation overhead. To alleviate this problem, we propose a novel framework to train an accuracy predictor under few training samples. The framework consists ofdata augmentation methods and an ensemble learning algorithm. The data augmentation methods calibrate weak labels and inject noise to feature space. The ensemble learning algorithm, termed cascade bagging, trains two-level models by sampling data and features. In the end, the advantages of above methods are proved in the Performance Prediciton Track of CVPR2021 1st Lightweight NAS Challenge. Our code is made public at: https://github.com/dlongry/Solutionto-CVPR2021-NAS-Track2.