arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2307.01288cs.LGcs.AI
收藏

用共识应对可解释机器学习中的分歧

Fighting the disagreement in Explainable Machine Learning with consensus

Antonio Jesus Banegas-Luna, Carlos Martınez-Cortes, Horacio Perez-Sanchez

AI总结:

本文针对可解释机器学习中不同解释算法结果相互矛盾的问题,在已知规则的合成数据集上系统评估了六种共识函数,并提出一种更公平且能产生更一致、更准确解释的新共识函数。

摘要:

机器学习(ML)模型通常因其预测准确性而受到重视。然而,在某些科学领域中,模型的内部运作方式与其准确性同样重要。为了理解 ML 模型内部如何工作,使用可解释性算法是首选方案。遗憾的是,尽管可用的算法多种多样,它们在解释模型时常常产生分歧,导致相互矛盾的解释。为了解决这一问题,可以在模型被解释之后应用共识函数。然而,该问题并未被完全解决,因为最终结果将取决于所选择的共识函数以及其他因素。本文针对五个 ML 模型的解释评估了六种共识函数。这些模型事先在四个内部规则已知的合成数据集上完成训练。随后,使用与模型无关的局部和全局可解释性算法对这些模型进行解释。最后,使用六种不同的函数计算共识,其中包括一种由作者提出的函数。结果表明,所提出的函数比其他函数更公平,并能提供更一致、更准确的解释。

英文摘要:

Machine learning (ML) models are often valued by the accuracy of their predictions. However, in some areas of science, the inner workings of models are as relevant as their accuracy. To understand how ML models work internally, the use of interpretability algorithms is the preferred option. Unfortunately, despite the diversity of algorithms available, they often disagree in explaining a model, leading to contradictory explanations. To cope with this issue, consensus functions can be applied once the models have been explained. Nevertheless, the problem is not completely solved because the final result will depend on the selected consensus function and other factors. In this paper, six consensus functions have been evaluated for the explanation of five ML models. The models were previously trained on four synthetic datasets whose internal rules were known in advance. The models were then explained with model-agnostic local and global interpretability algorithms. Finally, consensus was calculated with six different functions, including one developed by the authors. The results demonstrated that the proposed function is fairer than the others and provides more consistent and accurate explanations.

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。

↑