| Summary: | Pruning unimportant parameters can allow deep neural networks (DNNs) to reduce their heavy computation and memory requirements. A <italic>saliency metric</italic> estimates which parameters can be safely pruned with little impact on the classification performance of the DNN. Many saliency metrics have been proposed, each within the context of a wider pruning algorithm. The result is that it is difficult to separate the effectiveness of the saliency metric from the wider pruning algorithm that surrounds it. Similar-looking saliency metrics can yield very different results because of apparently minor design choices. We propose a novel taxonomy of saliency metrics based on four mostly-orthogonal principal components. We show that a broad range of metrics from the pruning literature can be grouped according to these components. Our taxonomy serves as a guide to prior work, and allows us to construct new saliency metrics by exploring novel combinations of our taxonomic components. We perform the first in-depth experimental investigation of more than 300 saliency metrics made up of existing techniques and new combinations of components. Our results provide decisive answers to open research questions. In particular, we demonstrate the importance of reduction and scaling when pruning groups of weights. We also propose a novel scaling method based on the number of weights transitively removed. We find that some of our constructed metrics can outperform the best existing state-of-the-art metrics for convolutional neural network channel pruning. We find further that our novel scaling method improves existing saliency metrics.
|
|---|
