基于分层代理规则集的机器学习模型行为可视化研究
Visual Exploration of Machine Learning Model Behavior with Hierarchical Surrogate Rule Sets
摘要：
模型解释的一个潜在解决方案是训练一个代理模型：一个更透明的模型，它近似于要解释的模型的行为。通常，由于分类规则或决策树的基于逻辑的表达的可理解性而使用分类规则或决策树。但是，决策树可能会生长得太深，规则集可能会变得太大，无法近似复杂的模型。与决策树上必须共享祖先节点（条件）的路径不同，规则更加灵活。然而，规则的非结构化视觉表示使得很难进行跨规则的推理。为了解决这些问题，我们提出了一个工作流程，其中包括新的算法和交互式解决方案。首先，我们提出了分层代理规则（HSR），一个算法，生成分层规则的基础上，用户定义的参数。我们还贡献了SuRE，一个可视化分析（VA）系统，集成了HSR和交互式代理规则可视化。特别是，我们提出了一种新的特征对齐树，以克服现有的规则可视化的缺点。我们评估算法的参数敏感性，时间性能，并与代理决策树比较，发现它的规模合理，在许多方面优于决策树。我们还评估了可视化和VA系统的可用性研究与24名志愿者和观察性研究与7个领域的专家。我们的调查表明，参与者可以使用特征对齐树来执行非常高的准确性，非平凡的任务。我们还讨论了许多有趣的观察，可以为未来的研究设计有效的基于规则的VA系统是有用的。
英文摘要：
One of the potential solutions for model interpretation is to train a surrogate model: a more transparent model that approximates the behavior of the model to be explained. Typically, classification rules or decision trees are used due to the intelligibility of their logic-based expressions. However, decision trees can grow too deep and rule sets can become too large to approximate a complex model. Unlike paths on a decision tree that must share ancestor nodes (conditions), rules are more flexible. However, the unstructured visual representation of rules makes it hard to make inferences across rules. To address these issues, we present a workflow that includes novel algorithmic and interactive solutions. First, we present Hierarchical Surrogate Rules (HSR), an algorithm that generates hierarchical rules based on user-defined parameters. We also contribute SuRE, a visual analytics (VA) system that integrates HSR and interactive surrogate rule visualizations. Particularly, we present a novel feature-aligned tree to overcome the shortcomings of existing rule visualizations. We evaluate the algorithm in terms of parameter sensitivity, time performance, and comparison with surrogate decision trees and find that it scales reasonably well and outperforms decision trees in many respects. We also evaluate the visualization and the VA system by a usability study with 24 volunteers and an observational study with 7 domain experts. Our investigation shows that the participants can use feature-aligned trees to perform non-trivial tasks with very high accuracy. We also discuss many interesting observations that can be useful for future research on designing effective rule-based VA systems.
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。
