论文标题
增量排列功能重要性（IPFI）：朝着数据流的在线说明
Incremental Permutation Feature Importance (iPFI): Towards Online Explanations on Data Streams
论文作者
论文摘要
到目前为止，可解释的人工智能（XAI）主要集中在静态学习方案上。我们对逐步采样数据的动态场景感兴趣，并且学习以增量而不是批处理模式进行。我们寻求有效的增量算法来计算特征重要性（FI）度量，特别是基于具有类似于置换特征重要性的缺乏特征的特征边缘化的增量FI度量（PFI）。我们提出了一种称为IPFI的高效，模型不足的算法，以逐步估算此措施，并在包括概念漂移（概念漂移）在内的动态建模条件下进行估算。我们证明了关于期望和差异方面的近似质量的理论保证。为了验证我们的理论发现和与传统批处理PFI相比，我们的方法的疗效，我们对具有和没有概念漂移的基准数据进行了多项实验研究。
Explainable Artificial Intelligence (XAI) has mainly focused on static learning scenarios so far. We are interested in dynamic scenarios where data is sampled progressively, and learning is done in an incremental rather than a batch mode. We seek efficient incremental algorithms for computing feature importance (FI) measures, specifically, an incremental FI measure based on feature marginalization of absent features similar to permutation feature importance (PFI). We propose an efficient, model-agnostic algorithm called iPFI to estimate this measure incrementally and under dynamic modeling conditions including concept drift. We prove theoretical guarantees on the approximation quality in terms of expectation and variance. To validate our theoretical findings and the efficacy of our approaches compared to traditional batch PFI, we conduct multiple experimental studies on benchmark data with and without concept drift.
