"Why Should I Trust Interactive Learners?" Explaining Interactive Queries of Classifiers to Users
This addresses the issue of user trust in interactive machine learning systems, which is incremental by adding explanations to existing interactive learning frameworks.
The paper tackles the problem of interactive learning systems being black boxes by proposing explanatory interactive learning, where the learner explains its queries to users, and shows this boosts predictive performance, explanatory power, and trust in experiments with text and image classification.
Although interactive learning puts the user into the loop, the learner remains mostly a black box for the user. Understanding the reasons behind queries and predictions is important when assessing how the learner works and, in turn, trust. Consequently, we propose the novel framework of explanatory interactive learning: in each step, the learner explains its interactive query to the user, and she queries of any active classifier for visualizing explanations of the corresponding predictions. We demonstrate that this can boost the predictive and explanatory powers of and the trust into the learned model, using text (e.g. SVMs) and image classification (e.g. neural networks) experiments as well as a user study.