Exploring extreme parameter compression for pre-trained language models

Benyou Wang, Yuxin Ren, Lifeng Shang, Xin Jiang, Qun Liu

Keywords: pre-trained language models, tensor decomposition, compression, BERT

Abstract:

Recent work explored the potential of large-scale Transformer-based pre-trained models, especially Pre-trained Language Models (PLMs) in natural language processing. This raises many concerns from various perspectives, e.g., financial costs and carbon emissions.
Compressing PLMs like BERT with negligible performance loss for faster inference and cheaper deployment has attracted much attention. In this work, we aim to explore larger compression ratios for PLMs, among which tensor decomposition is a potential but under-investigated one. By comparing existing decomposition methods, Tucker decomposition is found to be parameter-efficient for compression. Two decomposition and reconstruction protocols are further proposed to improve the effectiveness and efficiency of Tucker decomposition in parameter compression.
Our compressed BERT with ${1}/{7}$ parameters in Transformer layers performs on-par with, sometimes slightly better than the original BERT in GLUE benchmark. A tiny version achieves 96.7\% performance of BERT-base with $ {1}/{48} $ encoder parameters (i.e., less than 2M parameters excluding the embedding layer) and \textbf{$2.7 \times$} faster on inference. To show that the proposed method is orthogonal to existing compression methods like knowledge distillation, we also explore the benefit of the proposed method on a distilled BERT.

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2205.10036/code)