EdgeFormer: A Parameter-Efficient Transformer for On-Device Seq2seq Generation

Tao Ge, Si-Qing Chen, Furu Wei


Abstract
We introduce EdgeFormer – a parameter-efficient Transformer for on-device seq2seq generation under the strict computation and memory constraints. Compared with the previous parameter-efficient Transformers, EdgeFormer applies two novel principles for cost-effective parameterization, allowing it to perform better given the same parameter budget; moreover, EdgeFormer is further enhanced by layer adaptation innovation that is proposed for improving the network with shared layers.Extensive experiments show EdgeFormer can effectively outperform previous parameter-efficient Transformer baselines and achieve competitive results under both the computation and memory constraints. Given the promising results, we release EdgeLM – the pretrained version of EdgeFormer, which is the first publicly available pretrained on-device seq2seq model that can be easily fine-tuned for seq2seq tasks with strong results, facilitating on-device seq2seq generation in practice.
Anthology ID:
2022.emnlp-main.741
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
10786–10798
Language:
URL:
https://aclanthology.org/2022.emnlp-main.741
DOI:
10.18653/v1/2022.emnlp-main.741
Bibkey:
Cite (ACL):
Tao Ge, Si-Qing Chen, and Furu Wei. 2022. EdgeFormer: A Parameter-Efficient Transformer for On-Device Seq2seq Generation. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 10786–10798, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
EdgeFormer: A Parameter-Efficient Transformer for On-Device Seq2seq Generation (Ge et al., EMNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.emnlp-main.741.pdf