通过基于实例的解释和编辑模型输入直观地评估ML模型可靠性
Intuitively Assessing ML Model Reliability through Example-Based Explanations and Editing Model Inputs
摘要：
可解释性方法旨在帮助用户建立信任并理解机器学习模型的功能。然而，现有的方法通常依赖于抽象、复杂的可视化，这些可视化与手头的任务映射得很差，或者需要非平凡的机器学习专业知识来解释。在这里，我们提出了两个可视化分析模块，便于直观地评估模型的可靠性。为了帮助用户更好地表征和推理模型的不确定性，我们可视化了给定输入的最近邻居的原始和聚合信息。使用交互式编辑器，用户可以以语义上有意义的方式操作此输入，确定对输出的影响，并与他们先前的期望进行比较。我们评估我们的接口使用心电图节拍分类的案例研究。与基线特征重要性界面相比，我们发现14名医生能够更好地将模型的不确定性与域相关因素对齐，并建立对其能力和局限性的直觉。
英文摘要：
Interpretability methods aim to help users build trust in and understand the capabilities of machine learning models. However, existing approaches often rely on abstract, complex visualizations that poorly map to the task at hand or require non-trivial ML expertise to interpret. Here, we present two visual analytics modules that facilitate an intuitive assessment of model reliability. To help users better characterize and reason about a model's uncertainty, we visualize raw and aggregate information about a given input's nearest neighbors. Using an interactive editor, users can manipulate this input in semantically-meaningful ways, determine the effect on the output, and compare against their prior expectations. We evaluate our interface using an electrocardiogram beat classification case study. Compared to a baseline feature importance interface, we find that 14 physicians are better able to align the model's uncertainty with domain-relevant factors and build intuition about its capabilities and limitations.
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。
