Pruning unimportant parameters can allow deep neural networks (DNNs) to reduce their heavy computation and memory requirements. A saliency metric 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 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 not only serves as a guide to prior work, but allows us to construct new saliency metrics by exploring novel combinations of our taxonomic components. We perform an in-depth experimental investigation of more than 300 saliency metrics. Our results provide decisive answers to open research questions, and demonstrate the importance of reduction and scaling when pruning groups of weights. We find that some of our constructed metrics can outperform the best existing state-of-the-art metrics for convolutional neural network channel pruning.
翻译:深度神经网络(DNNs)可以降低其沉重的计算和记忆要求。一个显著的衡量指标估计参数可以安全地调整,对DNN的分类性能没有多大影响。已经提出了许多突出的衡量指标,每个指标都是在更广泛的运行算法范围内提出的。结果是,很难将显性指标的有效性与周围更为广泛的运行算法区分开来。类似的显性指标由于设计选择显然很小,可以产生非常不同的结果。我们提出一个基于四个主要组成部分的显著指标的分类方法。我们表明,从修读文献中得出的一系列广泛的计量指标可以按照这些组成部分进行分组。我们的分类不仅可以指导先前的工作,而且还使我们能够通过探索我们分类组成部分的新组合来建立新的显著指标。我们对300多个显著指标进行深入的实验性调查。我们的结果为公开研究问题提供了决定性的答案,并表明在压动中模型的模型组合中,我们能够发现某些现有变压式模型的模型。