Reweighted Proximal Pruning for Large-Scale Language RepresentationDownload PDF

Sep 25, 2019 (edited Dec 24, 2019)ICLR 2020 Conference Blind SubmissionReaders: Everyone
  • Original Pdf: pdf
  • TL;DR: We develop the pruning algorithm Reweighted Proximal Pruning (RPP), which achieves the first effective weight pruning result on large-scale pre-trained language representation model-BERT.
  • Abstract: Recently, pre-trained language representation flourishes as the mainstay of the natural language understanding community, e.g., BERT. These pre-trained language representations can create state-of-the-art results on a wide range of downstream tasks. Along with continuous significant performance improvement, the size and complexity of these pre-trained neural models continue to increase rapidly. Is it possible to compress these large-scale language representation models? How will the pruned language representation affect the downstream multi-task transfer learning objectives? In this paper, we propose Reweighted Proximal Pruning (RPP), a new pruning method specifically designed for a large-scale language representation model. Through experiments on SQuAD and the GLUE benchmark suite, we show that proximal pruned BERT keeps high accuracy for both the pre-training task and the downstream multiple fine-tuning tasks at high prune ratio. RPP provides a new perspective to help us analyze what large-scale language representation might learn. Additionally, RPP makes it possible to deploy a large state-of-the-art language representation model such as BERT on a series of distinct devices (e.g., online servers, mobile phones, and edge devices).
  • Keywords: Language Representation, Machine Learning, Deep Learning, Optimizer, Statistical Learning, Model Compression
12 Replies