arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2304.03113stat.MLcs.LG
收藏

通过因果结构学习实现高效的SAGE估计

Efficient SAGE Estimation via Causal Structure Learning

University of Vienna(维也纳大学);LMU Munich(慕尼黑大学)

Christoph Luther, Gunnar König, Moritz Grosse-Wentrup

AI总结:

提出 $d$-SAGE 方法,利用因果结构学习识别特征与目标间的条件独立性以跳过零剩余贡献计算,从而在保证准确性的同时显著加速 SAGE 值的近似估计。

摘要:

Shapley Additive Global Importance (SAGE) 值是一种具有理论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,其精确计算需要在指数级的特征集合上计算特征的剩余性能贡献。这在计算上非常昂贵,特别是因为估计剩余贡献需要从条件分布中进行采样。因此,SAGE 近似算法仅考虑了一小部分特征集。我们提出了 $d$-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(CIs)意味着零剩余贡献,因此可以跳过其计算。为了识别 CIs,我们利用因果结构学习(CSL)来推断一个图,该图将数据中的(条件)独立性编码为 $d$-分离。这在计算上更加高效,因为一次性图推断和 $d$-分离查询的开销与剩余贡献评估的开销相比可以忽略不计。我们通过实验证明,$d$-SAGE 能够实现 SAGE 值的高效且准确的估计。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑