The rapid development of large pre-trained language models has greatly increased the demand for model compression techniques, among which quantization is a popular solution. In this paper, we propose BinaryBERT, which pushes BERT quantization to the limit by weight binarization. We find that a binary BERT is hard to be trained directly than a ternary counterpart due to its complex and irregular loss landscape. Therefore, we propose ternary weight splitting, which initializes BinaryBERT by equivalently splitting from a half-sized ternary network. The binary model thus inherits the good performance of the ternary one, and can be further enhanced by fine-tuning the new architecture after splitting. Empirical results show that our BinaryBERT has only a slight performance drop compared with the full-precision model while being 24x smaller, achieving the state-of-the-art compression results on the GLUE and SQuAD benchmarks.
@article{arxiv.2012.15701,
title = {BinaryBERT: Pushing the Limit of BERT Quantization},
author = {Haoli Bai and Wei Zhang and Lu Hou and Lifeng Shang and Jing Jin and Xin Jiang and Qun Liu and Michael Lyu and Irwin King},
journal= {arXiv preprint arXiv:2012.15701},
year = {2021}
}