arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.04289cs.LGstat.ML
收藏

可解释矩阵--随机森林分类集成全局和局部可解释性的可视化

Explainable Matrix -- Visualization for Global and Local Interpretability of Random Forest Classification Ensembles

Federal Institute of São Paulo (IFSP)(圣保罗联邦学院(IFSP));University of São Paulo (USP)(圣保罗大学(USP));Dalhousie University(达尔豪斯大学)

Mário Popolin Neto, Fernando V. Paulovich

摘要:

在过去的几十年中,分类模型已被证明是必不可少的机器学习工具,因为它们在各个领域中具有潜力和适用性。近年来,北方的大多数研究人员一直致力于改进定量指标,尽管缺乏有关模型的决策信息,这些指标传达。这种模式最近发生了变化,除了表格和数字之外,帮助解释模型决策的策略越来越重要。作为这一趋势的一部分,可视化技术已被广泛用于支持分类模型的可解释性,其中重点关注基于规则的模型。尽管取得了这些进展,但现有的方法在视觉可扩展性方面存在限制,并且大型和复杂模型的可视化,例如由随机森林(RF)技术产生的模型,仍然是一个挑战。在本文中,我们提出了可解释矩阵(ExMatrix),一种新的可视化方法RF可解释性,可以处理大量的规则模型。它采用了一个简单而强大的矩阵式视觉隐喻,其中行是规则,列是特征,单元格是规则谓词,从而可以分析整个模型并审计分类结果。通过不同的例子证实了ExMatrix的适用性,展示了如何在实践中使用它来提高RF模型的可解释性。

英文摘要:

Over the past decades, classification models have proven to be essential machine learning tools given their potential and applicability in various domains. In these years, the north of the majority of the researchers had been to improve quantitative metrics, notwithstanding the lack of information about models' decisions such metrics convey. This paradigm has recently shifted, and strategies beyond tables and numbers to assist in interpreting models' decisions are increasing in importance. Part of this trend, visualization techniques have been extensively used to support classification models' interpretability, with a significant focus on rule-based models. Despite the advances, the existing approaches present limitations in terms of visual scalability, and the visualization of large and complex models, such as the ones produced by the Random Forest (RF) technique, remains a challenge. In this paper, we propose Explainable Matrix (ExMatrix), a novel visualization method for RF interpretability that can handle models with massive quantities of rules. It employs a simple yet powerful matrix-like visual metaphor, where rows are rules, columns are features, and cells are rules predicates, enabling the analysis of entire models and auditing classification results. ExMatrix applicability is confirmed via different examples, showing how it can be used in practice to promote RF models interpretability.

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。

↑