Machine Guides, Human Supervises: Interactive Learning with Global Explanations
This addresses the challenge of robust interactive learning for AI systems, though it appears incremental as it builds on existing explanatory interactive learning methods.
The paper tackles the problem of interactive learning where a machine guides a human supervisor to select informative examples for a classifier using global explanations, and it shows that this approach avoids overselling model quality and performs comparably or better than other strategies in simulations.
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.