Neural Networks are known to be sensitive to initialisation. The methods that rely on neural networks for feature ranking are not robust since they can have variations in their ranking when the model is initialized and trained with different random seeds. In this work, we introduce a novel method based on parameter averaging to estimate accurate and robust feature importance in tabular data setting, referred as XTab. We first initialize and train multiple instances of a shallow network (referred as local masks) with "different random seeds" for a downstream task. We then obtain a global mask model by "averaging the parameters" of local masks. We show that although the parameter averaging might result in a global model with higher loss, it still leads to the discovery of the ground-truth feature importance more consistently than an individual model does. We conduct extensive experiments on a variety of synthetic and real-world data, demonstrating that the XTab can be used to obtain the global feature importance that is not sensitive to sub-optimal model initialisation.
翻译:已知神经网络对初始化十分敏感。 依赖神经网络进行特征排序的方法并不健全, 因为它们在模型初始化和以不同随机种子进行训练时, 其排名会有所不同。 在这项工作中, 我们引入了一种新颖的方法, 其依据是平均参数, 用以估计表格数据设置中的准确和稳健特征重要性, 称为 XTab 。 我们首先为下游任务初始化和培训多个浅质网络( 称为本地面罩 ) 的“ 不同随机种子 ” 。 然后我们通过“ 保存本地面罩的参数” 获得一个全球掩码模型。 我们显示, 虽然平均参数可能导致损失更高的全球模型, 但仍然导致发现地面真相特征的重要性, 比单个模型更加一致。 我们在各种合成和真实世界数据上进行了广泛的实验, 表明 XTab 可用于获取对亚最佳模型初始化不敏感的全球特征重要性 。