PGB: One-Shot Pruning for BERT via Weight Grouping and Permutation
This addresses the computational inefficiency of BERT for deployment, though it is incremental as it builds on existing pruning techniques.
The paper tackles the problem of slow inference and high memory usage in large pretrained language models like BERT by proposing PGB, a one-shot pruning method that achieves high compression and sparsity while preserving accuracy, outperforming state-of-the-art structured pruning methods in computational cost and accuracy.
Large pretrained language models such as BERT suffer from slow inference and high memory usage, due to their huge size. Recent approaches to compressing BERT rely on iterative pruning and knowledge distillation, which, however, are often too complicated and computationally intensive. This paper proposes a novel semi-structured one-shot pruning method for BERT, called $\textit{Permutation and Grouping for BERT}$ (PGB), which achieves high compression efficiency and sparsity while preserving accuracy. To this end, PGB identifies important groups of individual weights by permutation and prunes all other weights as a structure in both multi-head attention and feed-forward layers. Furthermore, if no important group is formed in a particular layer, PGB drops the entire layer to produce an even more compact model. Our experimental results on BERT$_{\text{BASE}}$ demonstrate that PGB outperforms the state-of-the-art structured pruning methods in terms of computational cost and accuracy preservation.