paper-with-me

홈 › Papers

Connection Sensitivity Matters for Training-free DARTS: From Architecture-Level Scoring to Operation-Level Sensitivity Analysis

2021-06-22 · Miao Zhang, Wei Huang, Li Wang

The recently proposed training-free NAS methods abandon the training phase and design various zero-cost proxies as scores to identify excellent architectures, arousing extreme computational efficiency for neural architecture search. In this paper, we raise an interesting problem: can we properly measure the operation importance in DARTS through a training-free way, with avoiding the parameter-intensive bias? We investigate this question through the lens of edge connectivity, and provide an affirmative answer by defining a connectivity concept, ZERo-cost Operation Sensitivity (ZEROS), to score the importance of candidate operations in DARTS at initialization. By devising an iterative and data-agnostic manner in utilizing ZEROS for NAS, our novel trial leads to a framework called training free differentiable architecture search (FreeDARTS). Based on the theory of Neural Tangent Kernel (NTK), we show the proposed connectivity score provably negatively correlated with the generalization bound of DARTS supernet after convergence under gradient descent training. In addition, we theoretically explain how ZEROS implicitly avoids parameter-intensive bias in selecting architectures, and empirically show the searched architectures by FreeDARTS are of comparable size. Extensive experiments have been conducted on a series of search spaces, and results have demonstrated that FreeDARTS is a reliable and efficient baseline for neural architecture search.

📄 PDF Abstract BibTeX arXiv:2106.11542

Code (0)

등록된 구현이 없습니다.

Tasks

Computational EfficiencyNetwork PruningNeural Architecture SearchSensitivity

Methods 이 논문이 사용한 방법론

Differentiable NAS 설명 없음
DARTS Differentiable Architecture Search (DART) is a method for efficient architecture search. The search space is made continuous so that the architecture can be optimized with…

Similar Papers 제목 키워드 기반

Differentiable Architecture Search with Random Features

2022-08-18 · CVPR 2023 1 · Xuanyang Zhang, Yonggang Li, Xiangyu Zhang, Yongtao Wang 외

Differentiable architecture search (DARTS) has significantly promoted the development of NAS techniques because of its high search efficiency and effectiveness but suffers from performance collapse. In this paper, we mak…

Neural Architecture Search

Operation-Level Early Stopping for Robustifying Differentiable NAS

2023-09-21 · NeurIPS 2023 11

Differentiable NAS (DARTS) is a simple and efficient neural architecture search method that has been extensively adopted in various machine learning tasks. % Nevertheless, DARTS still encounters several robustness issue…

Partial Connection Based on Channel Attention for Differentiable Neural Architecture Search

2022-08-01 · Yu Xue, Jiafeng Qin

Differentiable neural architecture search (DARTS), as a gradient-guided search method, greatly reduces the cost of computation and speeds up the search. In DARTS, the architecture parameters are introduced to the candida…

Neural Architecture Search

Operation-level Progressive Differentiable Architecture Search

2023-02-11 · Xunyu Zhu, Jian Li, Yong liu, Weiping Wang

Differentiable Neural Architecture Search (DARTS) is becoming more and more popular among Neural Architecture Search (NAS) methods because of its high search efficiency and low compute cost. However, the stability of DAR…

Neural Architecture Search

ROME: Robustifying Memory-Efficient NAS via Topology Disentanglement and Gradient Accumulation

2020-11-23 · ICCV 2023 1 · Xiaoxing Wang, Xiangxiang Chu, Yuda Fan, Zhexi Zhang 외

Albeit being a prevalent architecture searching approach, differentiable architecture search (DARTS) is largely hindered by its substantial memory cost since the entire supernet resides in the memory. This is where the s…

DisentanglementNeural Architecture Search