期刊
IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS
卷 27, 期 2, 页码 1427-1437出版社
IEEE COMPUTER SOC
DOI: 10.1109/TVCG.2020.3030354
关键词
Visualization; Random forests; Radio frequency; Decision trees; Scalability; Predictive models; Vegetation; Random forest visualization; logic rules visualization; classification model interpretability; explainable artificial intelligence
资金
- Qualification Program of the Federal Institute of Sao Paulo (IFSP)
- Natural Sciences and Engineering Research Council of Canada (NSERC)
Classification models are crucial tools in various domains, but visualizing large and complex models like Random Forest remains a challenge. The new ExMatrix method utilizes a matrix-like visual metaphor to enhance interpretability and analysis of massive rule-based models.
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据