LPZero: Language Model Zero-cost Proxy Search from Zero

Peijie Dong, Lujun Li, Xiang Liu, Zhenheng Tang, Xuebo Liu, Qiang Wang, Xiaowen Chu


Abstract
Despite the outstanding performance, Neural Architecture Search (NAS) is criticized for massive computation. Recently, Zero-shot NAS has emerged as a promising approach by exploiting Zero-cost (ZC) proxies, which markedly reduce computational demands. Despite this, existing ZC proxies heavily rely on expert knowledge and incur significant trial-and-error costs. Particularly in NLP tasks, most existing ZC proxies fail to surpass the performance of the naive baseline. To address these challenges, we introduce a novel framework, LPZero, which is the first to automatically design zero-cost (ZC) proxies for various tasks, achieving higher ranking consistency than human-designed proxies. Specifically, we model the ZC proxy as a symbolic equation and incorporate a unified proxy search space that encompasses existing ZC proxies, which are composed of a predefined set of mathematical symbols. To heuristically search for the best ZC proxy, LPZero incorporates genetic programming to find the optimal symbolic composition. We propose a Predictive-Pruning Strategy (PPS), which preemptively eliminates unpromising proxies, thereby mitigating the risk of proxy degradation. Extensive experiments on FlexiBERT, GPT-2, and LLaMA-7B demonstrate LPZero’s superior ranking ability and performance on downstream tasks compared to current approaches.
Anthology ID:
2024.findings-emnlp.502
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2024
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8592–8614
Language:
URL:
https://aclanthology.org/2024.findings-emnlp.502
DOI:
Bibkey:
Cite (ACL):
Peijie Dong, Lujun Li, Xiang Liu, Zhenheng Tang, Xuebo Liu, Qiang Wang, and Xiaowen Chu. 2024. LPZero: Language Model Zero-cost Proxy Search from Zero. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 8592–8614, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
LPZero: Language Model Zero-cost Proxy Search from Zero (Dong et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-emnlp.502.pdf