Building Optimal Neural Architectures using Interpretable Knowledge
CVPR 2024(2024)
摘要
Neural Architecture Search is a costly practice. The fact that a search space
can span a vast number of design choices with each architecture evaluation
taking nontrivial overhead makes it hard for an algorithm to sufficiently
explore candidate networks. In this paper, we propose AutoBuild, a scheme which
learns to align the latent embeddings of operations and architecture modules
with the ground-truth performance of the architectures they appear in. By doing
so, AutoBuild is capable of assigning interpretable importance scores to
architecture modules, such as individual operation features and larger macro
operation sequences such that high-performance neural networks can be
constructed without any need for search. Through experiments performed on
state-of-the-art image classification, segmentation, and Stable Diffusion
models, we show that by mining a relatively small set of evaluated
architectures, AutoBuild can learn to build high-quality architectures directly
or help to reduce search space to focus on relevant areas, finding better
architectures that outperform both the original labeled ones and ones found by
search baselines. Code available at
https://github.com/Ascend-Research/AutoBuild
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要