This is the public, feature-limited version of the conference webpage. After Registration and login please visit the full version.

Movement Pruning: Adaptive Sparsity by Fine-Tuning

Victor Sanh, Thomas Wolf, Alexander Rush

Poster Session 2 (more posters)
on 2020-12-08T09:00:00-08:00 - 2020-12-08T11:00:00-08:00
Abstract: Magnitude pruning is a widely used strategy for reducing model size in pure supervised learning; however, it is less effective in the transfer learning regime that has become standard for state-of-the-art natural language processing applications. We propose the use of movement pruning, a simple, deterministic first-order weight pruning method that is more adaptive to pretrained model fine-tuning. We give mathematical foundations to the method and compare it to existing zeroth- and first-order pruning methods. Experiments show that when pruning large pretrained language models, movement pruning shows significant improvements in high-sparsity regimes. When combined with distillation, the approach achieves minimal accuracy loss with down to only 3% of the model parameters.

Preview Video and Chat

To see video, interact with the author and ask questions please use registration and login.