Masked Autoencoders Are Robust Neural Architecture Search Learners

arXiv:2311.12086v2 Announce Type: replace
Abstract: Neural Architecture Search (NAS) currently relies heavily on labeled data, which is both expensive and time-consuming to acquire. In this paper, we propose a novel NAS framework based on Masked Autoencoders (MAE) that eliminates the need for labeled data during the search process. By replacing the supervised learning objective with an image reconstruction task, our approach enables the robust discovery of network architectures without compromising performance and generalization ability. Additionally, we address the problem of …

abstract architecture arxiv autoencoders cs.lg cs.ne data framework nas neural architecture search novel paper process robust search type