We propose a graph-oriented attention-based explainability method for tabular data. Tasks involving tabular data have been solved mostly using traditional tree-based machine learning models which have the challenges of feature selection and engineering. With that in mind, we consider a transformer architecture for tabular data, which is amenable to explainability, and present a novel way to leverage self-attention mechanism to provide explanations by taking into account the attention matrices of all layers as a whole. The matrices are mapped to a graph structure where groups of features correspond to nodes and attention values to arcs. By finding the maximum probability paths in the graph, we identify groups of features providing larger contributions to explain the model's predictions. To assess the quality of multi-layer attention-based explanations, we compare them with popular attention-, gradient-, and perturbation-based explanability methods.

翻译：本文提出了一种面向图结构的注意力可解释性方法，适用于表格数据。传统上，表格数据任务多采用基于树的机器学习模型解决，但这类方法面临特征选择与工程化的挑战。基于此，我们采用适用于表格数据的Transformer架构——该架构天然具备可解释性，并提出一种创新方式，通过整体考量所有层的注意力矩阵来利用自注意力机制提供解释。我们将注意力矩阵映射为图结构，其中特征组对应节点，注意力权重对应弧线。通过寻找图中的最大概率路径，可识别出对模型预测贡献最大的特征组。为评估多层注意力解释的质量，我们将其与流行的基于注意力、梯度及扰动的可解释性方法进行了对比。