Copula for Instance-wise Feature Selection and Ranking

The identification of feature correlations can minimize the redundancy of features. Yet, in the literature of instance-wise Instance-wise feature selection and ranking methods feature selection and ranking methods [Chen et al., 2018, can achieve a good selection of task-friendly Yoon et al., 2019, Abid et al., 2019, Masoomi et al., 2020, features for each sample in the context of neural Wu and Liu, 2018] that follow the context of neural networks, networks. However, existing approaches that the dependencies between features has not been considered assume feature subsets to be independent are imperfect manifestly. For instance, L2X [Chen et al., 2018] performs when considering the dependency between a feature selection for maximizing the mutual information features. To address this limitation, we propose between selected feature subsets and corresponding outputs.