Salvato in:
Dettagli Bibliografici
Autori principali: Chen, Zhen-Song, Ding, Hong-Wei, Wang, Xian-Jia, Pedrycz, Witold
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2503.18646
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913754303692800
author Chen, Zhen-Song
Ding, Hong-Wei
Wang, Xian-Jia
Pedrycz, Witold
author_facet Chen, Zhen-Song
Ding, Hong-Wei
Wang, Xian-Jia
Pedrycz, Witold
contents Neural architecture search (NAS) provides a systematic framework for automating the design of neural network architectures, yet its widespread adoption is hindered by prohibitive computational requirements. Existing zero-cost proxy methods, while reducing search overhead, demonstrate inadequate performance in architecture ranking tasks, particularly for Transformer-based models where they often underperform simple parameter counting metrics. Current automated proxy discovery approaches suffer from extended search times, susceptibility to data overfitting, and structural complexity. This paper introduces a novel zero-cost proxy methodology that quantifies model capacity through efficient weight statistics computation while decomposing Transformer architectures into functionally distinct sub-modules, thereby optimizing the balance of their contributions to overall performance. Our comprehensive evaluation demonstrates the superiority of this approach, achieving a Spearman's rho of 0.76 and Kendall's tau of 0.53 on the FlexiBERT benchmark. The proposed method exhibits exceptional computational efficiency while maintaining robust performance across diverse NAS benchmark tasks, offering a practical solution for large-scale architecture search.
format Preprint
id arxiv_https___arxiv_org_abs_2503_18646
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ZeroLM: Data-Free Transformer Architecture Search for Language Models
Chen, Zhen-Song
Ding, Hong-Wei
Wang, Xian-Jia
Pedrycz, Witold
Computation and Language
Neural architecture search (NAS) provides a systematic framework for automating the design of neural network architectures, yet its widespread adoption is hindered by prohibitive computational requirements. Existing zero-cost proxy methods, while reducing search overhead, demonstrate inadequate performance in architecture ranking tasks, particularly for Transformer-based models where they often underperform simple parameter counting metrics. Current automated proxy discovery approaches suffer from extended search times, susceptibility to data overfitting, and structural complexity. This paper introduces a novel zero-cost proxy methodology that quantifies model capacity through efficient weight statistics computation while decomposing Transformer architectures into functionally distinct sub-modules, thereby optimizing the balance of their contributions to overall performance. Our comprehensive evaluation demonstrates the superiority of this approach, achieving a Spearman's rho of 0.76 and Kendall's tau of 0.53 on the FlexiBERT benchmark. The proposed method exhibits exceptional computational efficiency while maintaining robust performance across diverse NAS benchmark tasks, offering a practical solution for large-scale architecture search.
title ZeroLM: Data-Free Transformer Architecture Search for Language Models
topic Computation and Language
url https://arxiv.org/abs/2503.18646