Explaining the decision process of machine learning algorithms is nowadays crucial for both model's performance enhancement and human comprehension. This can be achieved by assessing the variable importance of single variables, even for high-capacity non-linear methods, e.g. Deep Neural Networks (DNNs). While only removal-based approaches, such as Permutation Importance (PI), can bring statistical validity, they return misleading results when variables are correlated. Conditional Permutation Importance (CPI) bypasses PI's limitations in such cases. However, in high-dimensional settings, where high correlations between the variables cancel their conditional importance, the use of CPI as well as other methods leads to unreliable results, besides prohibitive computation costs. Grouping variables statistically via clustering or some prior knowledge gains some power back and leads to better interpretations. In this work, we introduce BCPI (Block-Based Conditional Permutation Importance), a new generic framework for variable importance computation with statistical guarantees handling both single and group cases. Furthermore, as handling groups with high cardinality (such as a set of observations of a given modality) are both time-consuming and resource-intensive, we also introduce a new stacking approach extending the DNN architecture with sub-linear layers adapted to the group structure. We show that the ensuing approach extended with stacking controls the type-I error even with highly-correlated groups and shows top accuracy across benchmarks. Furthermore, we perform a real-world data analysis in a large-scale medical dataset where we aim to show the consistency between our results and the literature for a biomarker prediction.

解释机器学习算法的决策过程对模型性能提升和人类理解至关重要，通过评估单个变量的重要性来实现，甚至对于高容量的非线性方法，如深度神经网络（DNNs）。在高维设置中，引入了BCPI（基于块的条件排列重要性）作为一种新的通用框架来计算变量的重要性，具备统计保证并处理单个和群组情况。此外，通过将DNN架构扩展为适用于群组结构的次线性层，我们还引入了一种新的堆叠方法，以处理高基数群组，该方法在高度相关的群组中控制了一类错误，并在基准测试中展现了顶级准确性。此外，我们对大规模医学数据集进行了实际数据分析，旨在展示生物标志物预测方面的研究结果与文献的一致性。

高维情况下的变量重要性需要分组