论文标题
部分可观测时空混沌系统的无模型预测
Sub-network Multi-objective Evolutionary Algorithm for Filter Pruning
论文作者
论文摘要
过滤器修剪是在深神经网络（DNN）中实现模型压缩和加速的常见方法。一些研究将过滤器修剪为组合优化问题，因此使用进化算法（EA）来修剪DNNS的修剪过滤器。但是，由于解决方案空间的复杂性，很难在合理的时间内找到令人满意的折衷解决方案。为了解决此问题，我们首先基于完整模型的子网络制定多目标优化问题，并提出了用于过滤器修剪的子网络多目标进化算法（SMOEA）。通过逐步修剪卷积层，Smoea可以获得具有更好性能的轻质修剪结果。在CIFAR-10的VGG-14模型上进行了验证，可以验证拟议的SMOEA的有效性。具体而言，16.56％参数的修剪模型的准确性仅降低0.28％，这比广泛使用的流行过滤器修剪标准要好。
Filter pruning is a common method to achieve model compression and acceleration in deep neural networks (DNNs).Some research regarded filter pruning as a combinatorial optimization problem and thus used evolutionary algorithms (EA) to prune filters of DNNs. However, it is difficult to find a satisfactory compromise solution in a reasonable time due to the complexity of solution space searching. To solve this problem, we first formulate a multi-objective optimization problem based on a sub-network of the full model and propose a Sub-network Multiobjective Evolutionary Algorithm (SMOEA) for filter pruning. By progressively pruning the convolutional layers in groups, SMOEA can obtain a lightweight pruned result with better performance.Experiments on VGG-14 model for CIFAR-10 verify the effectiveness of the proposed SMOEA. Specifically, the accuracy of the pruned model with 16.56% parameters decreases by 0.28% only, which is better than the widely used popular filter pruning criteria.
