Timezone: »

Extreme Compression for Pre-trained Transformers Made Simple and Efficient
Xiaoxia Wu · Zhewei Yao · Minjia Zhang · Conglong Li · Yuxiong He

Tue Nov 29 09:00 AM -- 11:00 AM (PST) @ Hall J #632

Extreme compression, particularly ultra-low bit precision (binary/ternary) quantization, has been proposed to fit large NLP models on resource-constraint devices. However, to preserve the accuracy for such aggressive compression schemes, cutting-edge methods usually introduce complicated compression pipelines, e.g., multi-stage expensive knowledge distillation with extensive hyperparameter tuning. Also, they oftentimes focus less on smaller transformer models that have already been heavily compressed via knowledge distillation and lack a systematic study to show the effectiveness of their methods.In this paper, we perform a very comprehensive systematic study to measure the impact of many key hyperparameters and training strategies from previous. As a result, we find out that previous baselines for ultra-low bit precision quantization are significantly under-trained. Based on our study, we propose a simple yet effective compression pipeline for extreme compression. Our simplified pipeline demonstrates that(1) we can skip the pre-training knowledge distillation to obtain a 5-layer \bert while achieving better performance than previous state-of-the-art methods, like TinyBERT; (2) extreme quantization plus layer reduction is able to reduce the model size by 50x, resulting in new state-of-the-art results on GLUE tasks.

Author Information

Xiaoxia Wu (Microsoft)
Zhewei Yao (UC Berkeley)
Minjia Zhang (Microsoft)
Conglong Li (Microsoft)
Yuxiong He (Microsoft)

More from the Same Authors