This paper proposes a reliable neural network pruning algorithm by setting up a scientific control. Existing pruning methods have developed various hypotheses to approximate the importance of filters to the network and then execute filter pruning accordingly. To increase the reliability of the results, we prefer to have a more rigorous research design by including a scientific control group as an essential part to minimize the effect of all factors except the association between the filter and expected network output. Acting as a control group, knockoff feature is generated to mimic the feature map produced by the network filter, but they are conditionally independent of the example label given the real feature map. We theoretically suggest that the knockoff condition can be approximately preserved given the information propagation of network layers. Besides the real feature map on an intermediate layer, the corresponding knockoff feature is brought in as another auxiliary input signal for the subsequent layers. Redundant filters can be discovered in the adversarial process of different features. Through experiments, we demonstrate the superiority of the proposed algorithm over state-of-the-art methods. For example, our method can reduce 57.8% parameters and 60.2% FLOPs of ResNet-101 with only 0.01% top-1 accuracy loss on ImageNet. The code is available at https://github.com/huawei-noah/Pruning/tree/master/SCOP_NeurIPS2020.

翻译：本文通过建立科学控制, 提出了一个可靠的神经网络运行算法 。 现有的修剪方法已经开发了各种假设, 以近似过滤器对网络的重要性, 然后相应执行过滤器运行。 为了提高结果的可靠性, 我们更希望有一个更加严格的研究设计, 包括一个科学控制组, 作为最大限度地减少除过滤器和预期网络输出之间关联之外所有因素影响的重要部分。 作为控制组, 生成了取假功能来模仿由网络过滤器生成的功能地图, 但是它们有条件地独立于基于真实功能映射的示例标签 。 我们理论上建议, 由于网络层的信息传播, 关闭条件可以大致保存 。 除了在中间层的真实功能映射外, 相应的开关功能被引入为下一个层的又一个辅助输入信号 。 在不同特性的对抗过程中可以发现红化过滤器 。 我们通过实验, 展示了提议的算法优于20 状态方法, 但是它们有条件地独立于 。 例如, 我们的方法可以减少57.8%的参数, 和60.2%的 FLOPs- LOPs- ResNet/ frainormainal amal mages.