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 1902.03501cs.LGcs.HCstat.ML
收藏

评估机器学习模型的局部可解释性

Assessing the Local Interpretability of Machine Learning Models

Haverford College(哈弗福德学院);University of Arizona(亚利桑那大学);University of Utah(犹他大学)

Dylan Slack, Sorelle A. Friedler, Carlos Scheidegger, Chitradeep Dutta Roy

摘要:

随着机器学习工具的日益普及,人们呼吁通过模型的可解释性来实现问责制。但是,人类可以解释机器学习模型意味着什么,如何评估这一点?我们专注于在机器学习文献中引入的可解释性的两个定义:可模拟性(用户在给定输入上运行模型的能力)和“如果”局部可解释性(用户在输入的局部变化下正确确定模型预测的能力,给定模型原始预测的知识)。通过一项有1,000名参与者的用户研究,我们测试了人类在模拟可模拟性和“如果”局部可解释性的任务上是否表现良好,这些任务通常被认为是局部可解释的。为了跟踪模型的相对可解释性,我们采用了一个简单的度量标准,即可模拟性任务的运行时操作计数。我们发现的证据表明,随着操作数量的增加,参与者的准确性在当地的可解释性任务下降。此外,这一证据与决策树和逻辑回归模型是可解释的并且比神经网络更可解释的常见直觉是一致的。

英文摘要:

The increasing adoption of machine learning tools has led to calls for accountability via model interpretability. But what does it mean for a machine learning model to be interpretable by humans, and how can this be assessed? We focus on two definitions of interpretability that have been introduced in the machine learning literature: simulatability (a user's ability to run a model on a given input) and "what if" local explainability (a user's ability to correctly determine a model's prediction under local changes to the input, given knowledge of the model's original prediction). Through a user study with 1,000 participants, we test whether humans perform well on tasks that mimic the definitions of simulatability and "what if" local explainability on models that are typically considered locally interpretable. To track the relative interpretability of models, we employ a simple metric, the runtime operation count on the simulatability task. We find evidence that as the number of operations increases, participant accuracy on the local interpretability tasks decreases. In addition, this evidence is consistent with the common intuition that decision trees and logistic regression models are interpretable and are more interpretable than neural networks.

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。

↑