paper-with-me

홈 › Papers

A Transformer-based Neural Architecture Search Method

2025-05-02 · Shang Wang, Huanrong Tang, Jianquan Ouyang

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.

📄 PDF Abstract BibTeX arXiv:2505.01314

Code (1)

ra225/mo-trans 공식 구현 pytorch

Tasks

DecoderNeural Architecture Search

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Multi-Head Attention 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Adam 설명 없음
Attention 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Position-Wise Feed-Forward Layer 설명 없음

Similar Papers 제목 키워드 기반

Neural Architecture Search on Efficient Transformers and Beyond

2022-07-28 · Zexiang Liu, Dong Li, Kaiyue Lu, Zhen Qin 외

Recently, numerous efficient Transformers have been proposed to reduce the quadratic computational complexity of standard Transformers caused by the Softmax attention. However, most of them simply swap Softmax with an ef…

Computational Efficiencyimage-classificationImage ClassificationMachine Translation+1

HyTAS: A Hyperspectral Image Transformer Architecture Search Benchmark and Analysis

2024-07-23 · Fangqin Zhou, Mert Kilickaya, Joaquin Vanschoren, Ran Piao

Hyperspectral Imaging (HSI) plays an increasingly critical role in precise vision tasks within remote sensing, capturing a wide spectrum of visual data. Transformer architectures have significantly enhanced HSI task perf…

Model Discovery

GLiT: Neural Architecture Search for Global and Local Image Transformer

2021-07-07 · ICCV 2021 10 · BoYu Chen, Peixia Li, Chuming Li, Baopu Li 외

We introduce the first Neural Architecture Search (NAS) method to find a better transformer architecture for image recognition. Recently, transformers without CNN-based backbones are found to achieve impressive performan…

image-classificationImage ClassificationNeural Architecture Search

UniNet: Unified Architecture Search with Convolution, Transformer, and MLP

2021-10-08 · Jihao Liu, Hongsheng Li, Guanglu Song, Xin Huang 외

Recently, transformer and multi-layer perceptron (MLP) architectures have achieved impressive results on various vision tasks. A few works investigated manually combining those operators to design visual network architec…

Image Classificationobject-detectionObject DetectionSemantic Segmentation

The Evolved Transformer

2019-01-30 · David R. So, Chen Liang, Quoc V. Le

Recent works have highlighted the strength of the Transformer architecture on sequence tasks while, at the same time, neural architecture search (NAS) has begun to outperform human-designed models. Our goal is to apply N…

Machine TranslationNeural Architecture Search