论文标题
神经网络中特征选择的嵌入式方法
Embedded methods for feature selection in neural networks
论文作者
论文摘要
现代神经网络体系结构的代表性能力使它们成为具有高维功能集的各种应用程序中的默认选择。但是，这些高维和潜在嘈杂的特征与黑匣子模型（如神经网络）相结合，对这些模型的可解释性，可推广性和训练时间产生负面影响。在这里，我提出了两种用于特征选择的集成方法，可以将它们直接纳入参数学习。其中之一涉及添加一个液位层和执行顺序的重量修剪。另一种是基于灵敏度的方法。我对两种反对置换特征重要性（PFI）的方法进行了基准测试 - 通用特征排名方法和随机基线。建议的方法是用于特征选择的可行方法，在测试数据集中始终超过了基线 - MNIST，ISLISET和HAR。我们只需几行代码将它们添加到任何现有模型中。
The representational capacity of modern neural network architectures has made them a default choice in various applications with high dimensional feature sets. But these high dimensional and potentially noisy features combined with the black box models like neural networks negatively affect the interpretability, generalizability, and the training time of these models. Here, I propose two integrated approaches for feature selection that can be incorporated directly into the parameter learning. One of them involves adding a drop-in layer and performing sequential weight pruning. The other is a sensitivity-based approach. I benchmarked both the methods against Permutation Feature Importance (PFI) - a general-purpose feature ranking method and a random baseline. The suggested approaches turn out to be viable methods for feature selection, consistently outperform the baselines on the tested datasets - MNIST, ISOLET, and HAR. We can add them to any existing model with only a few lines of code.
