A Transformer-based Neural Architecture Search Method

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Shang, Tang, Huanrong, Ouyang, Jianquan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915587956932608
author Wang, Shang
Tang, Huanrong
Ouyang, Jianquan
author_facet Wang, Shang
Tang, Huanrong
Ouyang, Jianquan
contents This paper presents a neural architecture search method based on Transformer architecture, searching cross multihead attention computation ways for different number of encoder and decoder combinations. In order to search for neural network structures with better translation results, we considered perplexity as an auxiliary evaluation metric for the algorithm in addition to BLEU scores and iteratively improved each individual neural network within the population by a multi-objective genetic algorithm. Experimental results show that the neural network structures searched by the algorithm outperform all the baseline models, and that the introduction of the auxiliary evaluation metric can find better models than considering only the BLEU score as an evaluation metric.
format Preprint
id arxiv_https___arxiv_org_abs_2505_01314
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Transformer-based Neural Architecture Search Method
Wang, Shang
Tang, Huanrong
Ouyang, Jianquan
Computation and Language
Artificial Intelligence
Machine Learning
Neural and Evolutionary Computing
This paper presents a neural architecture search method based on Transformer architecture, searching cross multihead attention computation ways for different number of encoder and decoder combinations. In order to search for neural network structures with better translation results, we considered perplexity as an auxiliary evaluation metric for the algorithm in addition to BLEU scores and iteratively improved each individual neural network within the population by a multi-objective genetic algorithm. Experimental results show that the neural network structures searched by the algorithm outperform all the baseline models, and that the introduction of the auxiliary evaluation metric can find better models than considering only the BLEU score as an evaluation metric.
title A Transformer-based Neural Architecture Search Method
topic Computation and Language
Artificial Intelligence
Machine Learning
Neural and Evolutionary Computing
url https://arxiv.org/abs/2505.01314