English

Towards Aggregating Weighted Feature Attributions

Machine Learning 2019-01-30 v1 Artificial Intelligence Machine Learning

Abstract

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.

Keywords

Cite

@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

R2 v1 2026-06-23T07:24:55.625Z