Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Hu, Yiming, Chu, Xiangxiang, Wang, Yong
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2311.12086
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918309192007680
author Hu, Yiming
Chu, Xiangxiang
Wang, Yong
author_facet Hu, Yiming
Chu, Xiangxiang
Wang, Yong
contents Neural Architecture Search (NAS) relies heavily on labeled data, which is labor-intensive and time-consuming to obtain. In this paper, we propose a novel NAS method based on an unsupervised paradigm, specifically Masked Autoencoders (MAE), thereby eliminating the need for labeled data. By replacing the supervised learning objective with an image reconstruction task, our approach enables the efficient discovery of network architectures without compromising performance and generalization ability. Additionally, we address the problem of performance collapse encountered in the widely-used Differentiable Architecture Search (DARTS) in the unsupervised setting by designing a hierarchical decoder. Extensive experiments across various datasets demonstrate the effectiveness and robustness of our method, offering empirical evidence of its superiority over the counterparts.
format Preprint
id arxiv_https___arxiv_org_abs_2311_12086
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Robust MAE-Driven NAS: From Mask Reconstruction to Architecture Innovation
Hu, Yiming
Chu, Xiangxiang
Wang, Yong
Machine Learning
Neural and Evolutionary Computing
Neural Architecture Search (NAS) relies heavily on labeled data, which is labor-intensive and time-consuming to obtain. In this paper, we propose a novel NAS method based on an unsupervised paradigm, specifically Masked Autoencoders (MAE), thereby eliminating the need for labeled data. By replacing the supervised learning objective with an image reconstruction task, our approach enables the efficient discovery of network architectures without compromising performance and generalization ability. Additionally, we address the problem of performance collapse encountered in the widely-used Differentiable Architecture Search (DARTS) in the unsupervised setting by designing a hierarchical decoder. Extensive experiments across various datasets demonstrate the effectiveness and robustness of our method, offering empirical evidence of its superiority over the counterparts.
title Robust MAE-Driven NAS: From Mask Reconstruction to Architecture Innovation
topic Machine Learning
Neural and Evolutionary Computing
url https://arxiv.org/abs/2311.12086