# Efficient Differentiable Neural Architecture Search with Meta Kernels

Source: [Efficient Differentiable Neural Architecture Search with Meta Kernels](<https://www.sota2.com/research/paper/68fa66c81e209131cea1234d>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:58:21.378Z

Authors: Shoufa Chen, Yunpeng Chen, Shuicheng Yan, Jiashi Feng

Published: 2019-12-10T15:08:50.000Z

## Abstract

The searching procedure of neural architecture search (NAS) is notoriously time consuming and cost prohibitive.To make the search space continuous, most existing gradient-based NAS methods relax the categorical choice of a particular operation to a softmax over all possible operations and calculate the weighted sum of multiple features, resulting in a large memory requirement and a huge computation burden. In this work, we propose an efficient and novel search strategy with meta kernels. We directly encode the supernet from the perspective on convolution kernels and "shrink" multiple convolution kernel candidates into a single one before these candidates operate on the input feature. In this way, only a single feature is generated between two intermediate nodes. The memory for storing intermediate features and the resource budget for conducting convolution operations are both reduced remarkably. Despite high efficiency, our search strategy can search in a more fine-grained way than existing works and increases the capacity for representing possible networks. We demonstrate the effectiveness of our search strategy by conducting extensive experiments. Specifically, our method achieves 77.0% top-1 accuracy on ImageNet benchmark dataset with merely 357M FLOPs, outperforming both EfficientNet and MobileNetV3 under the same FLOPs constraints. Compared to models discovered by the start-of-the-art NAS method, our method achieves the same (sometimes even better) performance, while faster by three orders of magnitude.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1912.04749>)

[PDF](<https://arxiv.org/pdf/1912.04749.pdf>)
