标题： 神经网络剪枝的现状如何？ 显示英文标题

标题： What is the State of Neural Network Pruning?

摘要： 神经网络剪枝——通过移除参数来减小网络规模的任务——近年来已成为大量研究的主题。 我们对文献进行了元分析，包括对剪枝方法的概述以及文献中的一致发现。 在汇总81篇论文的结果并在受控条件下剪枝数百个模型后，我们最明确的发现是，该领域缺乏标准化的基准和指标。 这种不足相当严重，以至于很难相互比较剪枝技术，或确定过去三十年该领域取得了多少进展。 为了解决这种情况，我们指出了当前实践中的问题，提出了具体的解决方案，并引入了ShrinkBench，这是一个开源框架，用于促进剪枝方法的标准化评估。 我们使用ShrinkBench比较了各种剪枝技术，并表明其全面的评估可以防止在比较剪枝方法时出现常见陷阱。 显示英文摘要

摘要： Neural network pruning---the task of reducing the size of a network by removing parameters---has been the subject of a great deal of work in recent years. We provide a meta-analysis of the literature, including an overview of approaches to pruning and consistent findings in the literature. After aggregating results across 81 papers and pruning hundreds of models in controlled conditions, our clearest finding is that the community suffers from a lack of standardized benchmarks and metrics. This deficiency is substantial enough that it is hard to compare pruning techniques to one another or determine how much progress the field has made over the past three decades. To address this situation, we identify issues with current practices, suggest concrete remedies, and introduce ShrinkBench, an open-source framework to facilitate standardized evaluations of pruning methods. We use ShrinkBench to compare various pruning techniques and show that its comprehensive evaluation can prevent common pitfalls when comparing pruning methods.