Machine Guides, Human Supervises: Interactive Learning with Global Explanations

TL;DR

This paper presents explanatory guided learning (XGL), an interactive strategy where a machine uses global explanations to guide human supervisors in selecting informative training examples, improving model quality and robustness.

Contribution

The paper introduces XGL, a novel interactive learning method leveraging global explanations to guide human supervision, addressing limitations of local explanation-based strategies.

Findings

XGL avoids overselling the classifier's quality.

XGL performs comparably or better than existing strategies.

Global explanations effectively guide human-in-the-loop learning.

Abstract

We introduce explanatory guided learning (XGL), a novel interactive learning strategy in which a machine guides a human supervisor toward selecting informative examples for a classifier. The guidance is provided by means of global explanations, which summarize the classifier's behavior on different regions of the instance space and expose its flaws. Compared to other explanatory interactive learning strategies, which are machine-initiated and rely on local explanations, XGL is designed to be robust against cases in which the explanations supplied by the machine oversell the classifier's quality. Moreover, XGL leverages global explanations to open up the black-box of human-initiated interaction, enabling supervisors to select informative examples that challenge the learned model. By drawing a link to interactive machine teaching, we show theoretically that global explanations are a viable approach for guiding supervisors. Our simulations show that explanatory guided learning avoids overselling the model's quality and performs comparably or better than machine- and human-initiated interactive learning strategies in terms of model quality.