Current approaches for explaining machine learning models fall into two distinct classes: antecedent event influence and value attribution. The former leverages training instances to describe how much influence a training point exerts on a test point, while the latter attempts to attribute value to the features most pertinent to a given prediction. In this work, we discuss an algorithm, AVA: Aggregate Valuation of Antecedents, that fuses these two explanation classes to form a new approach to feature attribution that not only retrieves local explanations but also captures global patterns learned by a model. Our experimentation convincingly favors weighting and aggregating feature attributions via AVA.
@article{arxiv.1901.10040,
title = {Towards Aggregating Weighted Feature Attributions},
author = {Umang Bhatt and Pradeep Ravikumar and Jose M. F. Moura},
journal= {arXiv preprint arXiv:1901.10040},
year = {2019}
}
Comments
In AAAI-19 Workshop on Network Interpretability for Deep Learning