Reservoir Transformers
Sheng Shen, Alexei Baevski, Ari Morcos, Kurt Keutzer, Michael Auli, Douwe Kiela
Abstract
We demonstrate that transformers obtain impressive performance even when some of the layers are randomly initialized and never updated. Inspired by old and well-established ideas in machine learning, we explore a variety of non-linear “reservoir” layers interspersed with regular transformer layers, and show improvements in wall-clock compute time until convergence, as well as overall performance, on various machine translation and (masked) language modelling tasks.- Anthology ID:
- 2021.acl-long.331
- Volume:
- Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
- Month:
- August
- Year:
- 2021
- Address:
- Online
- Editors:
- Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
- Venues:
- ACL | IJCNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 4294–4309
- Language:
- URL:
- https://preview.aclanthology.org/build-pipeline-with-new-library/2021.acl-long.331/
- DOI:
- 10.18653/v1/2021.acl-long.331
- Cite (ACL):
- Sheng Shen, Alexei Baevski, Ari Morcos, Kurt Keutzer, Michael Auli, and Douwe Kiela. 2021. Reservoir Transformers. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 4294–4309, Online. Association for Computational Linguistics.
- Cite (Informal):
- Reservoir Transformers (Shen et al., ACL-IJCNLP 2021)
- PDF:
- https://preview.aclanthology.org/build-pipeline-with-new-library/2021.acl-long.331.pdf
- Data
- MultiNLI, SST, SST-2