English

Reservoir Transformers

Computation and Language 2021-06-03 v2

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.

Keywords

Cite

@article{arxiv.2012.15045,
  title  = {Reservoir Transformers},
  author = {Sheng Shen and Alexei Baevski and Ari S. Morcos and Kurt Keutzer and Michael Auli and Douwe Kiela},
  journal= {arXiv preprint arXiv:2012.15045},
  year   = {2021}
}

Comments

ACL 2021

R2 v1 2026-06-23T21:35:10.594Z