Movement Pruning: Adaptive Sparsity By Fine-tuning | Awesome LLM Papers Add your paper to Awesome LLM Papers

Movement Pruning: Adaptive Sparsity By Fine-tuning

Victor Sanh, Thomas Wolf, Alexander M. Rush . Arxiv 2020 – 166 citations

[Paper]   Search on Google Scholar   Search on Semantic Scholar
Applications Compositional Generalization Efficiency Fine Tuning Interdisciplinary Approaches Multimodal Semantic Representation

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.

Similar Work