一句话：提出用规则归纳刻画机器学习模型表现差的数据区域，辅助模型调试与集成。
机器学习模型在软件工程任务中预测准确率常不理想，误预测原因难以定位。本文提出一种面向已训练统计模型的调试技术：给定模型和带标签数据集，通过规则归纳生成可解释的规则，刻画模型表现特别差的数据子集。该方法可揭示训练数据或模型局限，并用于集成多个互补模型。作者通过案例研究评估，并展示在 Facebook 软件工程任务中提升预测模型准确率的应用。
While machine learning (ML) models play an increasingly prevalent role in many software engineering tasks, their prediction accuracy is often problematic. When these models do mispredict, it can be very difficult to isolate the cause. In this paper, we propose a technique that aims to facilitate the debugging process of trained statistical models. Given an ML model and a labeled data set, our method produces an interpretable characterization of the data on which the model performs particularly poorly. The output of our technique can be useful for understanding limitations of the training data or the model itself; it can also be useful for ensembling if there are multiple models with different strengths. We evaluate our approach through case studies and illustrate how it can be used to improve the accuracy of predictive models used for software engineering tasks within Facebook.
DOI 原文 ·
@inproceedings{paperbot6447,
title = {Explaining mispredictions of machine learning models using rule induction},
author = {Jürgen Cito and Isil Dillig and Seohyun Kim and Vijayaraghavan Murali and Satish Chandra},
booktitle = {FSE},
year = {2021},
doi = {10.1145/3468264.3468614}
}