EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

AutoPEFT : Automatic Configuration Search for Parameter-Efficient Fine-Tuning

Han Zhou, Xingchen Wan, Ivan Vulić, Anna Korhonen

Transactions of the Association for Computational Linguistics · 03.05.2024 · 12 · 525-542

DOI: 10.1162/tacl_a_00662 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Transactions of the Association for Computational Linguistics, online erschienen am 03.05.2024. Verfasst von Han Zhou und 3 weiteren Autor:innen. Die Arbeit wurde bisher 28-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Large pretrained language models are widely used in downstream NLP tasks via task- specific fine-tuning, but such procedures can be costly. Recently, Parameter-Efficient Fine-Tuning (PEFT) methods have achieved strong task performance while updating much fewer parameters than full model fine-tuning (FFT). However, it is non-trivial to make informed design choices on the PEFT configurations, such as their architecture, the number of tunable parameters, and even the layers in which the PEFT modules are inserted. Consequently, it is highly likely that the current, manually designed configurations are suboptimal in terms of their performance-efficiency trade-off. Inspired by advances in neural architecture search, we propose AutoPEFT for automatic PEFT configuration selection: We first design an expressive configuration search space with multiple representative PEFT modules as building blocks. Using multi-objective Bayesian optimization in a low-cost setup, we then discover a Pareto-optimal set of configurations with strong performance-cost trade-offs across different numbers of parameters that are also highly transferable across different tasks. Empirically, on GLUE and SuperGLUE tasks, we show that AutoPEFT-discovered configurations significantly outperform existing PEFT methods and are on par or better than FFT without incurring substantial training efficiency costs.

Zitieren

APA

Zhou, H., Wan, X., Vulić, I., & Korhonen, A. (2024). AutoPEFT : Automatic Configuration Search for Parameter-Efficient Fine-Tuning. Transactions of the Association for Computational Linguistics, 12, 525-542. https://doi.org/10.1162/tacl_a_00662

Vancouver

Zhou H, Wan X, Vulić I, Korhonen A. AutoPEFT : Automatic Configuration Search for Parameter-Efficient Fine-Tuning. Transactions of the Association for Computational Linguistics. 2024;12:525-542. doi:10.1162/tacl_a_00662

BibTeX
@article{Zhou2024,
  author = {Zhou, Han and Wan, Xingchen and Vulić, Ivan and Korhonen, Anna},
  title = {AutoPEFT : Automatic Configuration Search for Parameter-Efficient Fine-Tuning},
  journal = {Transactions of the Association for Computational Linguistics},
  year = {2024},
  volume = {12},
  pages = {525--542},
  doi = {10.1162/tacl_a_00662}
}
Kostenlos starten →