Research

The Lottery Ticket Hypothesis for the Pre-trained BERT Networks

Cite Paper Code

Authors

Categories

Efficient AI Natural Language Processing NeurIPS

In natural language processing (NLP), enormous pre-trained models like BERT have become the standard starting point for training on a range of downstream tasks, and similar trends are emerging in other areas of deep learning. In parallel, work on the lottery ticket hypothesis has shown that models for NLP and computer vision contain smaller matching subnetworks capable of training in isolation to full accuracy and transferring to other tasks. In this work, we combine these observations to assess whether such trainable, transferrable subnetworks exist in pre-trained BERT models. For a range of downstream tasks, we indeed find matching subnetworks at 40% to 90% sparsity. We find these subnetworks at (pre-trained) initialization, a deviation from prior NLP research where they emerge only after some amount of training. Subnetworks found on the masked language modeling task (the same task used to pre-train the model) transfer universally; those found on other tasks transfer in a limited fashion if at all. As large-scale pre-training becomes an increasingly central paradigm in deep learning, our results demonstrate that the main lottery ticket observations remain relevant in this context. Codes available at this https URL.

This paper has been published as a poster at the 2020 Neural Information Processing Systems (NeurIPS) conference.

Please cite our work using the BibTeX below.

@misc{chen2020lottery,
      title={The Lottery Ticket Hypothesis for Pre-trained BERT Networks}, 
      author={Tianlong Chen and Jonathan Frankle and Shiyu Chang and Sijia Liu and Yang Zhang and Zhangyang Wang and Michael Carbin},
      year={2020},
      eprint={2007.12223},
      archivePrefix={arXiv},
      primaryClass={cs.LG}
}