Introducing quest: a query-driven framework to explain classification models on tabular data

Abstract

Machine learning models are everywhere now; but only few of them are transparent in how they work. To remedy this, local explanations aim to show users how and why learned models produce a certain output for a given input (data sample). However, most existing approaches for are oriented around images or text data and, thus, cannot leverage the structure and properties of tabular data. Therefore, we present Quest, a new framework for generating explanations that are a better fit for tabular data. The main idea is to create explanations in the form of relational predicates (called queries hereafter) that approximate the behavior of a classifier around the given sample. In an initial evaluation, we show anecdotally how Quest can be used on a tabular data set compared to existing approaches that can be applied on tabular data.