arrow
Return

A zero-cost proxy model for NAS based on information quantity quantization encoding

delete2025-12-31
delete0
PRE
AI
Y
Yue Yang
J
Jing Lu
Z
Zhonghu Jing
L
Liangyuan Wang
D
Di Han
M
Menglan Hu
彭凯 (Kai Peng) *
DOI:10.1016/j.eswa.2025.130989delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
• First proposed quantization encoding for neural network architectures. • Built a zero-cost proxy model based on quantization encoding. • Achieved the best performance among fully zero-cost proxy models.

Journal

Expert Systems with Applications cover
Expert Systems with Applications
IF:
7.5
Papers:
2.9W
Citations:
10.2W

Organization

No organization information available