FlowerFormer: Empowering Neural Architecture Encoding using a Flow-aware Graph Transformer

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Hwang, Dongyeong, Kim, Hyunju, Kim, Sunwoo, Shin, Kijung
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914722211692544
author Hwang, Dongyeong
Kim, Hyunju
Kim, Sunwoo
Shin, Kijung
author_facet Hwang, Dongyeong
Kim, Hyunju
Kim, Sunwoo
Shin, Kijung
contents The success of a specific neural network architecture is closely tied to the dataset and task it tackles; there is no one-size-fits-all solution. Thus, considerable efforts have been made to quickly and accurately estimate the performances of neural architectures, without full training or evaluation, for given tasks and datasets. Neural architecture encoding has played a crucial role in the estimation, and graphbased methods, which treat an architecture as a graph, have shown prominent performance. For enhanced representation learning of neural architectures, we introduce FlowerFormer, a powerful graph transformer that incorporates the information flows within a neural architecture. FlowerFormer consists of two key components: (a) bidirectional asynchronous message passing, inspired by the flows; (b) global attention built on flow-based masking. Our extensive experiments demonstrate the superiority of FlowerFormer over existing neural encoding methods, and its effectiveness extends beyond computer vision models to include graph neural networks and auto speech recognition models. Our code is available at http://github.com/y0ngjaenius/CVPR2024_FLOWERFormer.
format Preprint
id arxiv_https___arxiv_org_abs_2403_12821
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle FlowerFormer: Empowering Neural Architecture Encoding using a Flow-aware Graph Transformer
Hwang, Dongyeong
Kim, Hyunju
Kim, Sunwoo
Shin, Kijung
Machine Learning
Artificial Intelligence
The success of a specific neural network architecture is closely tied to the dataset and task it tackles; there is no one-size-fits-all solution. Thus, considerable efforts have been made to quickly and accurately estimate the performances of neural architectures, without full training or evaluation, for given tasks and datasets. Neural architecture encoding has played a crucial role in the estimation, and graphbased methods, which treat an architecture as a graph, have shown prominent performance. For enhanced representation learning of neural architectures, we introduce FlowerFormer, a powerful graph transformer that incorporates the information flows within a neural architecture. FlowerFormer consists of two key components: (a) bidirectional asynchronous message passing, inspired by the flows; (b) global attention built on flow-based masking. Our extensive experiments demonstrate the superiority of FlowerFormer over existing neural encoding methods, and its effectiveness extends beyond computer vision models to include graph neural networks and auto speech recognition models. Our code is available at http://github.com/y0ngjaenius/CVPR2024_FLOWERFormer.
title FlowerFormer: Empowering Neural Architecture Encoding using a Flow-aware Graph Transformer
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2403.12821