NAS-BERT: Task-Agnostic and Adaptive-Size BERT Compression with Neural Architecture Search

TL;DR

NAS-BERT introduces a neural architecture search-based method to efficiently compress BERT into multiple models of varying sizes and latencies, supporting diverse deployment scenarios while maintaining task-agnostic applicability.

Contribution

The paper presents NAS-BERT, a novel NAS-based approach that produces multiple compressed BERT models of different sizes and latencies, trained on pre-training tasks for broad downstream use.

Findings

NAS-BERT outperforms previous compression methods in accuracy.

The method generates models suitable for various device constraints.

Compressed models are effective across multiple NLP benchmarks.

Abstract

While pre-trained language models (e.g., BERT) have achieved impressive results on different natural language processing tasks, they have large numbers of parameters and suffer from big computational and memory costs, which make them difficult for real-world deployment. Therefore, model compression is necessary to reduce the computation and memory cost of pre-trained models. In this work, we aim to compress BERT and address the following two challenging practical issues: (1) The compression algorithm should be able to output multiple compressed models with different sizes and latencies, in order to support devices with different memory and latency limitations; (2) The algorithm should be downstream task agnostic, so that the compressed models are generally applicable for different downstream tasks. We leverage techniques in neural architecture search (NAS) and propose NAS-BERT, an efficient method for BERT compression. NAS-BERT trains a big supernet on a search space containing a variety of architectures and outputs multiple compressed models with adaptive sizes and latency. Furthermore, the training of NAS-BERT is conducted on standard self-supervised pre-training tasks (e.g., masked language model) and does not depend on specific downstream tasks. Thus, the compressed models can be used across various downstream tasks. The technical challenge of NAS-BERT is that training a big supernet on the pre-training task is extremely costly. We employ several techniques including block-wise search, search space pruning, and performance approximation to improve search efficiency and accuracy. Extensive experiments on GLUE and SQuAD benchmark datasets demonstrate that NAS-BERT can find lightweight models with better accuracy than previous approaches, and can be directly applied to different downstream tasks with adaptive model sizes for different requirements of memory or latency.