The Shapley Additive Global Importance (SAGE) value is a theoretically appealing interpretability method that fairly attributes global importance to a model's features. However, its exact calculation requires the computation of the feature's surplus performance contributions over an exponential number of feature sets. This is computationally expensive, particularly because estimating the surplus contributions requires sampling from conditional distributions. Thus, SAGE approximation algorithms only take a fraction of the feature sets into account. We propose $d$-SAGE, a method that accelerates SAGE approximation. $d$-SAGE is motivated by the observation that conditional independencies (CIs) between a feature and the model target imply zero surplus contributions, such that their computation can be skipped. To identify CIs, we leverage causal structure learning (CSL) to infer a graph that encodes (conditional) independencies in the data as $d$-separations. This is computationally more efficient because the expense of the one-time graph inference and the $d$-separation queries is negligible compared to the expense of surplus contribution evaluations. Empirically we demonstrate that $d$-SAGE enables the efficient and accurate estimation of SAGE values.

翻译：Shapley加性全局重要性（SAGE）值是一种理论上具有吸引力的可解释性方法，能够公平地将全局重要性归因于模型的特征。然而，其精确计算需要对指数级数量的特征集计算特征的超额性能贡献。这在计算上代价高昂，特别是因为估计超额贡献需要从条件分布中采样。因此，SAGE近似算法仅考虑特征集的一小部分。我们提出$d$-SAGE，一种加速SAGE近似的方法。$d$-SAGE的动机在于观察到特征与模型目标之间的条件独立性（CI）意味着零超额贡献，从而可以跳过其计算。为了识别条件独立性，我们利用因果结构学习（CSL）推断出一张图，该图将数据中的（条件）独立性编码为$d$-分离。这在计算上更为高效，因为一次性图推断和$d$-分离查询的开销与超额贡献评估的开销相比微不足道。实验结果表明，$d$-SAGE能够实现SAGE值的高效准确估计。