The growing size of neural language models has led to increased attention in model compression. The two predominant approaches are pruning, which gradually removes weights from a pre-trained model, and distillation, which trains a smaller compact model to match a larger one. Pruning methods can significantly reduce the model size but hardly achieve large speedups as distillation. However, distillation methods require large amounts of unlabeled data and are expensive to train. In this work, we propose a task-specific structured pruning method CoFi (Coarse- and Fine-grained Pruning), which delivers highly parallelizable subnetworks and matches the distillation methods in both accuracy and latency, without resorting to any unlabeled data. Our key insight is to jointly prune coarse-grained (e.g., layers) and fine-grained (e.g., heads and hidden units) modules, which controls the pruning decision of each parameter with masks of different granularity. We also devise a layerwise distillation strategy to transfer knowledge from unpruned to pruned models during optimization. Our experiments on GLUE and SQuAD datasets show that CoFi yields models with over 10x speedups with a small accuracy drop, showing its effectiveness and efficiency compared to previous pruning and distillation approaches.

提出 CoFi（粗细粒度剪枝）方法，该方法结合了粗细粒度模块的剪枝决策，并采用分层蒸馏策略将知识从未剪枝模型转移到已剪枝模型，使模型同时拥有与蒸馏方法相当的精度和延迟优势，而无需使用无标注数据。在 GLUE 和 SQuAD 数据集上的实验表明，CoFi 方法在速度和精度方面相对于以前的剪枝和蒸馏方法具有更高的效率和效果。

结构化剪枝学习紧凑而精确的模型