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 2307.09779cs.LGcs.AI
收藏

借助ICECREAM超越单特征重要性

Beyond Single-Feature Importance with ICECREAM

University of Mannheim(曼海姆大学);Amazon(亚马逊)

Michael Oesterle, Patrick Blöbaum, Atalanti A. Mastakouri, Elke Kirschbaum

AI总结:

针对现有可解释性方法仅能分析单特征重要性的局限,提出基于信息论的ICECREAM方法衡量变量联盟对目标的影响,在可解释性与根因分析任务上性能优于现有最优方法。

摘要:

哪组特征导致了机器学习模型的某一特定输出?哪些组件引发了云计算应用的故障?本文通过“识别任意模型中常见与罕见事件的基于联盟的解释(ICECREAM)”方法来解决这类问题。具体而言,我们提出了一种基于信息论的量化指标,用于衡量变量联盟对目标变量分布的影响。这让我们能够识别出产生特定结果所必需的因素集合,而成熟的可解释性与因果贡献分析方法仅能将贡献分配给单个因素并按重要性排序。在合成数据与真实数据的实验中,我们表明ICECREAM在可解释性和根因分析任务上优于当前最优方法,在两项任务中均取得了出色的准确率。

英文摘要:

Which set of features was responsible for a certain output of a machine learning model? Which components caused the failure of a cloud computing application? These are just two examples of questions we are addressing in this work by Identifying Coalition-based Explanations for Common and Rare Events in Any Model (ICECREAM). Specifically, we propose an information-theoretic quantitative measure for the influence of a coalition of variables on the distribution of a target variable. This allows us to identify which set of factors is essential to obtain a certain outcome, as opposed to well-established explainability and causal contribution analysis methods which can assign contributions only to individual factors and rank them by their importance. In experiments with synthetic and real-world data, we show that ICECREAM outperforms state-of-the-art methods for explainability and root cause analysis, and achieves impressive accuracy in both tasks.

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。

↑