This paper evaluates the viability of using fixed language models for training text classification networks on low-end hardware. We combine language models with a CNN architecture and put together a comprehensive benchmark with 8 datasets covering single-label and multi-label classification of topic, sentiment, and genre. Our observations are distilled into a list of trade-offs, concluding that there are scenarios, where not fine-tuning a language model yields competitive effectiveness at faster training, requiring only a quarter of the memory compared to fine-tuning.
@article{arxiv.2305.02350,
title = {Using Language Models on Low-end Hardware},
author = {Fabian Ziegner and Janos Borst and Andreas Niekler and Martin Potthast},
journal= {arXiv preprint arXiv:2305.02350},
year = {2023}
}