Publication Details

Fighting Randomness With Randomness: Mitigating Optimisation Instability of Fine-Tuning Using Ensemble and Noise Regularisation

PECHER, B.; ČEGIŇ, J.; BELANEC, R.; SRBA, I.; ŠIMKO, J.; BIELIKOVÁ, M. Fighting Randomness With Randomness: Mitigating Optimisation Instability of Fine-Tuning Using Ensemble and Noise Regularisation. Findings of the Association for Computational Linguistics: EMNLP 2024. Miami: Association for Computational Linguistics, 2024. p. 11005-11044. ISBN: 979-8-8917-6168-1.
Czech title
Boj proti náhodnosti náhodnosťou: Zmierňovanie nestability optimalizácie pri doladení pomocou ansámblov a regularizácie šumom
Type
conference paper
Language
English
Authors
Keywords

NLP in resource-constrained settings, parameter-efficient-training, data-efficient training, data augmentation, fine-tuning, mitigating randomness, ensembling

Abstract

While fine-tuning of pre-trained language models generally helps to overcome the lack of labelled training samples, it also displays model performance instability. This instability mainly originates from randomness in initialisation or data shuffling. To address this, researchers either modify the training process or augment the available samples, which typically results in increased computational costs. We propose a new mitigation strategy, called Delayed Ensemble with Noisy Interpolation (DENI), that leverages the strengths of ensembling, noise regularisation and model interpolation, while retaining computational efficiency. We compare DENI with 9 representative mitigation strategies across 3 models, 4 tuning strategies and 7 text classification datasets. We show that: 1) DENI outperforms the best performing mitigation strategy (Ensemble), while using only a fraction of its cost; 2) the mitigation strategies are beneficial for parameter-efficient fine-tuning (PEFT) methods, outperforming full fine-tuning in specific cases; and 3) combining DENI with data augmentation often leads to even more effective instability mitigation.

Published
2024
Pages
11005–11044
Proceedings
Findings of the Association for Computational Linguistics: EMNLP 2024
ISBN
979-8-8917-6168-1
Publisher
Association for Computational Linguistics
Place
Miami
DOI
BibTeX
@inproceedings{BUT193319,
  author="PECHER, B. and ČEGIŇ, J. and BELANEC, R. and SRBA, I. and ŠIMKO, J. and BIELIKOVÁ, M.",
  title="Fighting Randomness With Randomness: Mitigating Optimisation Instability of Fine-Tuning Using Ensemble and Noise Regularisation",
  booktitle="Findings of the Association for Computational Linguistics: EMNLP 2024",
  year="2024",
  pages="11005--11044",
  publisher="Association for Computational Linguistics",
  address="Miami",
  doi="10.18653/v1/2024.findings-emnlp.644",
  isbn="979-8-8917-6168-1"
}
Back to top