DSEE: Dually Sparsity-embedded Efficient Tuning of Pre-trained Language Models

Xuxi Chen, Tianlong Chen, Weizhu Chen, Ahmed Hassan Awadallah, Zhangyang Wang, Yu Cheng


Abstract
Gigantic pre-trained models have become central to natural language processing (NLP), serving as the starting point for fine-tuning towards a range of downstream tasks. However, two pain points persist for this paradigm: (a) as the pre-trained models grow bigger (e.g., 175B parameters for GPT-3), even the fine-tuning process can be time-consuming and computationally expensive; (b) the fine-tuned model has the same size as its starting point by default, which is neither sensible due to its more specialized functionality, nor practical since many fine-tuned models will be deployed in resource-constrained environments. To address these pain points, we propose a framework for resource- and parameter-efficient fine-tuning by leveraging the sparsity prior in both weight updates and the final model weights. Our proposed framework, dubbed Dually Sparsity-Embedded Efficient Tuning (DSEE), aims to achieve two key objectives: (i) parameter efficient fine-tuning - by enforcing sparsity-aware low-rank updates on top of the pre-trained weights; and (ii) resource-efficient inference - by encouraging a sparse weight structure towards the final fine-tuned model. We leverage sparsity in these two directions by exploiting both unstructured and structured sparse patterns in pre-trained language models viaa unified approach. Extensive experiments and in-depth investigations, with diverse network backbones (i.e., BERT, RoBERTa, and GPT-2) on dozens of datasets, consistently demonstrate impressive parameter-/inference-efficiency, while maintaining competitive downstream performance. For instance, DSEE saves about 25% inference FLOPs while achieving comparable performance, with 0.5% trainable parameters on BERT. Codes are available at https://github.com/VITA-Group/DSEE.
Anthology ID:
2023.acl-long.456
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8208–8222
Language:
URL:
https://aclanthology.org/2023.acl-long.456
DOI:
10.18653/v1/2023.acl-long.456
Bibkey:
Cite (ACL):
Xuxi Chen, Tianlong Chen, Weizhu Chen, Ahmed Hassan Awadallah, Zhangyang Wang, and Yu Cheng. 2023. DSEE: Dually Sparsity-embedded Efficient Tuning of Pre-trained Language Models. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 8208–8222, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
DSEE: Dually Sparsity-embedded Efficient Tuning of Pre-trained Language Models (Chen et al., ACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.acl-long.456.pdf
Video:
 https://aclanthology.org/2023.acl-long.456.mp4