paper-with-me

Papers

SCARLET-NAS: Bridging the Gap between Stability and Scalability in Weight-sharing Neural Architecture Search

2019-08-16 · Xiangxiang Chu, Bo Zhang, Qingyuan Li, Ruijun Xu, Xudong Li

To discover powerful yet compact models is an important goal of neural architecture search. Previous two-stage one-shot approaches are limited by search space with a fixed depth. It seems handy to include an additional skip connection in the search space to make depths variable. However, it creates a large range of perturbation during supernet training and it has difficulty giving a confident ranking for subnetworks. In this paper, we discover that skip connections bring about significant feature inconsistency compared with other operations, which potentially degrades the supernet performance. Based on this observation, we tackle the problem by imposing an equivariant learnable stabilizer to homogenize such disparities. Experiments show that our proposed stabilizer helps to improve the supernet's convergence as well as ranking performance. With an evolutionary search backend that incorporates the stabilized supernet as an evaluator, we derive a family of state-of-the-art architectures, the SCARLET series of several depths, especially SCARLET-A obtains 76.9% top-1 accuracy on ImageNet. Code is available at https://github.com/xiaomi-automl/ScarletNAS.

📄 PDF Abstract BibTeX arXiv:1908.06022

Code (1)

xiaomi-automl/SCARLET-NAS 공식 구현 pytorch

Tasks

AutoMLImage ClassificationNeural Architecture Search

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
Depthwise Convolution Depthwise Convolution is a type of convolution where we apply a single convolutional filter for each input channel. In the regular 2D…
Pointwise Convolution Pointwise Convolution is a type of convolution that uses a 1x1 kernel: a kernel that iterates through every single point. This…
Depthwise Separable Convolution While standard convolution performs the channelwise and spatial-wise computation in one step, Depthwise Separable Convolution
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Batch Normalization 설명 없음
Inverted Residual Block 설명 없음

Similar Papers 제목 키워드 기반

Soft-Label Caching and Sharpening for Communication-Efficient Federated Distillation

2025-04-28 · Kitsuya Azuma, Takayuki Nishio, Yuichi Kitagawa, Wakako Nakano 외

Federated Learning (FL) enables collaborative model training across decentralized clients, enhancing privacy by keeping data local. Yet conventional FL, relying on frequent parameter-sharing, suffers from high communicat…

Federated Learning

Dynamics-incorporated Modeling Framework for Stability Constrained Scheduling Under High-penetration of Renewable Energy

2025-01-10 · IEEE TRANSACTIONS ON SUSTAINABLE ENERGY 2025 1 · Jinning Wang, Fangxing Li, Xin Fang, Hantao Cui 외

In this paper, a modularized modeling framework is designed to enable a dynamics-incorporated power system scheduling under high-penetration of renewable energy. This unique framework incorporates an adapted hybrid symbo…

Scheduling

Do Large Language Models Perform Latent Multi-Hop Reasoning without Exploiting Shortcuts?

2024-11-25 · Sohee Yang, Nora Kassner, Elena Gribovskaya, Sebastian Riedel 외

We evaluate how well Large Language Models (LLMs) latently recall and compose facts to answer multi-hop queries like "In the year Scarlett Johansson was born, the Summer Olympics were hosted in the country of". One major…

Li$_x$CoO$_2$ phase stability studied by machine learning-enabled scale bridging between electronic structure, statistical mechanics and phase field theories

2021-04-16 · Gregory H. Teichert, Sambit Das, Muratahan Aykol, Chirranjeevi Gopal 외

Li$_xTM$O$_2$ (TM={Ni, Co, Mn}) are promising cathodes for Li-ion batteries, whose electrochemical cycling performance is strongly governed by crystal structure and phase stability as a function of Li content at the atom…

Efficient High-Accuracy PDEs Solver with the Linear Attention Neural Operator

2025-10-19 · Ming Zhong, Zhenya Yan arxiv

Neural operators offer a powerful data-driven framework for learning mappings between function spaces, in which the transformer-based neural operator architecture faces a fundamental scalability-accuracy trade-off: softm…