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 2203.12701cs.AIcs.LG
收藏

基于特征属性算法的可控因素影响分析--以医学案例为例

On Understanding the Influence of Controllable Factors with a Feature Attribution Algorithm: a Medical Case Study

Swansea University(斯旺西大学);Nanyang Technological University(南洋理工大学)

Veera Raghava Reddy Kovvuri, Siyuan Liu, Monika Seisenberger, Berndt Müller, Xiuyi Fan

摘要:

特征属性XAI算法使其用户能够通过特征重要性计算深入了解大型数据集的底层模式。现有的特征属性算法对数据集中的所有特征进行均匀处理,这可能导致对改变特征值的后果的误解。在这项工作中,我们考虑分区功能成可控和不可控的部分,并提出了可控fActor特征属性(CAFA)的方法来计算可控功能的相对重要性。我们将CAFA应用于两个现有数据集和我们自己的COVID-19非药物控制措施数据集进行了实验。实验结果表明,使用CAFA,我们能够在解释中排除不可控特征的影响,同时保留完整的数据集进行预测。

英文摘要:

Feature attribution XAI algorithms enable their users to gain insight into the underlying patterns of large datasets through their feature importance calculation. Existing feature attribution algorithms treat all features in a dataset homogeneously, which may lead to misinterpretation of consequences of changing feature values. In this work, we consider partitioning features into controllable and uncontrollable parts and propose the Controllable fActor Feature Attribution (CAFA) approach to compute the relative importance of controllable features. We carried out experiments applying CAFA to two existing datasets and our own COVID-19 non-pharmaceutical control measures dataset. Experimental results show that with CAFA, we are able to exclude influences from uncontrollable features in our explanation while keeping the full dataset for prediction.

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。

↑