Bandits for Learning to Explain from Explanations
Machine Learning
2021-02-09 v1 Machine Learning
Abstract
We introduce Explearn, an online algorithm that learns to jointly output predictions and explanations for those predictions. Explearn leverages Gaussian Processes (GP)-based contextual bandits. This brings two key benefits. First, GPs naturally capture different kinds of explanations and enable the system designer to control how explanations generalize across the space by virtue of choosing a suitable kernel. Second, Explearn builds on recent results in contextual bandits which guarantee convergence with high probability. Our initial experiments hint at the promise of the approach.
Cite
@article{arxiv.2102.03815,
title = {Bandits for Learning to Explain from Explanations},
author = {Freya Behrens and Stefano Teso and Davide Mottin},
journal= {arXiv preprint arXiv:2102.03815},
year = {2021}
}
Comments
Accepted at the Explainable Agency in Artificial Intelligence Workshop, hosted at the 35th AAAI Conference on Artificial Intelligence, February 2-9, 2021