# Differentiable Neural Architecture Transformation for Reproducible Architecture Improvement

Source: [Differentiable Neural Architecture Transformation for Reproducible Architecture Improvement](<https://www.sota2.com/research/paper/68fa6b0b1e209131cea2ba93>)

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

Data updated: 2025-10-25T23:38:16.503Z

Authors: Do-Guk Kim, Heung-Chang Lee

Published: 2020-06-15T09:03:48.000Z

## Abstract

Recently, Neural Architecture Search (NAS) methods are introduced and show impressive performance on many benchmarks. Among those NAS studies, Neural Architecture Transformer (NAT) aims to improve the given neural architecture to have better performance while maintaining computational costs. However, NAT has limitations about a lack of reproducibility. In this paper, we propose differentiable neural architecture transformation that is reproducible and efficient. The proposed method shows stable performance on various architectures. Extensive reproducibility experiments on two datasets, i.e., CIFAR-10 and Tiny Imagenet, present that the proposed method definitely outperforms NAT and be applicable to other models and datasets.

## 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/2006.08231>)

[PDF](<https://arxiv.org/pdf/2006.08231.pdf>)