Stronger NAS with Weaker Predictors

Wu, Junru; Dai, Xiyang; Chen, Dongdong; Chen, Yinpeng; Liu, Mengchen; Yu, Ye; Wang, Zhangyang; Liu, Zicheng; Chen, Mei; Liu, Yuan

doi:10.48550/arxiv.2102.10490

Cited by 2 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Li et al propose block-wise progressive NAS [19,20] that consider the architectures is built by sequential blocks and search the architecture block by block. SGAS [21], GreedyNAS [36], and [17,41,34] progressively shrink the search space by dropping unpromising candidates. These progressive NAS methods require a much smaller exploration size, but their greedy nature hampers their search accuracy.…”

Section: Explore Wisely Early Methods Adopt Reinforcementmentioning

confidence: 99%

When NAS Meets Trees: An Efficient Algorithm for Neural Architecture Search

Qian¹,

Zhang²,

Li³

et al. 2022

Preprint

View full text Add to dashboard Cite

The key challenge in neural architecture search (NAS) is designing how to explore wisely in the huge search space. We propose a new NAS method called TNAS (NAS with trees), which improves search efficiency by exploring only a small number of architectures while also achieving a higher search accuracy. TNAS introduces an architecture tree and a binary operation tree, to factorize the search space and substantially reduce the exploration size. TNAS performs a modified bi-level Breadth-First Search in the proposed trees to discover a high-performance architecture. Impressively, TNAS finds the global optimal architecture on CIFAR-10 with test accuracy of 94.37% in four GPU hours in NAS-Bench-201. The average test accuracy is 94.35%, which outperforms the state-of-the-art. Code is available at: https://github.com/guochengqian/TNAS.

show abstract

Section: Explore Wisely Early Methods Adopt Reinforcementmentioning

confidence: 99%

When NAS Meets Trees: An Efficient Algorithm for Neural Architecture Search

Qian¹,

Zhang²,

Li³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…In general, reduced training can be found in many NAS works (Pham et al 2018;Zhou et al 2020), and different proxies have been proposed, e.g. searching for a model on a smaller dataset and then transferring the architecture to the larger target dataset (Real et al 2019;Mehrotra et al 2021), or incorporating a predictor into the search process (Wei et al 2020;Dudziak et al 2020;Wu et al 2021;Wen et al 2019).…”

Section: Related Workmentioning

confidence: 99%

Zero-Cost Operation Scoring in Differentiable Architecture Search

Xiang

Dudziak

Abdelfattah

et al. 2023

AAAI

View full text Add to dashboard Cite

We formalize and analyze a fundamental component of dif- ferentiable neural architecture search (NAS): local “opera- tion scoring” at each operation choice. We view existing operation scoring functions as inexact proxies for accuracy, and we find that they perform poorly when analyzed empir- ically on NAS benchmarks. From this perspective, we intro- duce a novel perturbation-based zero-cost operation scor- ing (Zero-Cost-PT) approach, which utilizes zero-cost prox- ies that were recently studied in multi-trial NAS but de- grade significantly on larger search spaces, typical for dif- ferentiable NAS. We conduct a thorough empirical evalu- ation on a number of NAS benchmarks and large search spaces, from NAS-Bench-201, NAS-Bench-1Shot1, NAS- Bench-Macro, to DARTS-like and MobileNet-like spaces, showing significant improvements in both search time and accuracy. On the ImageNet classification task on the DARTS search space, our approach improved accuracy compared to the best current training-free methods (TE-NAS) while be- ing over 10× faster (total searching time 25 minutes on a single GPU), and observed significantly better transferabil- ity on architectures searched on the CIFAR-10 dataset with an accuracy increase of 1.8 pp. Our code is available at: https://github.com/zerocostptnas/zerocost operation score.

show abstract

Stronger NAS with Weaker Predictors

Cited by 2 publications

References 0 publications

When NAS Meets Trees: An Efficient Algorithm for Neural Architecture Search

When NAS Meets Trees: An Efficient Algorithm for Neural Architecture Search

Zero-Cost Operation Scoring in Differentiable Architecture Search

Contact Info

Product

Resources

About