English

LPZero: Language Model Zero-cost Proxy Search from Zero

Computation and Language 2024-10-08 v1

Abstract

In spite of 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, \textbf{LPZero}, which is the first to automatically design 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 \textit{Rule-based Pruning Strategy (RPS),} 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.

Cite

@article{arxiv.2410.04808,
  title  = {LPZero: Language Model Zero-cost Proxy Search from Zero},
  author = {Peijie Dong and Lujun Li and Xiang Liu and Zhenheng Tang and Xuebo Liu and Qiang Wang and Xiaowen Chu},
  journal= {arXiv preprint arXiv:2410.04808},
  year   = {2024}
}

Comments

8 pages, 7 figures, 10 appendix

R2 v1 2026-06-28T19:10:48.513Z