Cate: Computation-aware neural architecture encoding with transformers
Recent works (White et al., 2020a; Yan et al., 2020) demonstrate the importance of
architecture encodings in Neural Architecture Search (NAS). These encodings encode …
architecture encodings in Neural Architecture Search (NAS). These encodings encode …
Learning low-rank representations for model compression
Z Zhu, Y Dong, Z Zhao - 2023 International Joint Conference …, 2023 - ieeexplore.ieee.org
Vector Quantization (VQ) is an appealing model compression method to obtain a tiny model
with less accuracy loss. While methods to obtain better codebooks and codes under fixed …
with less accuracy loss. While methods to obtain better codebooks and codes under fixed …
[图书][B] New Perspectives in Neural Architecture Search: Architecture Embeddings, Efficient Performance Estimations, and Their Applications
S Yan - 2022 - search.proquest.com
Neural architecture search (NAS) has made significant strides in recent years, but
challenges remain in terms of the stability of search performance and the high computational …
challenges remain in terms of the stability of search performance and the high computational …
Enhancing Neural Architecture Search by Upgrading Weak Components
X Qu, J Wang, J Liu, J Xiao - 2021 International Joint …, 2021 - ieeexplore.ieee.org
Neural Architecture Search (NAS) becomes increasingly popular due to the ability to liberate
the researchers from the complicated model design. However, typical NAS methods search …
the researchers from the complicated model design. However, typical NAS methods search …