Can I read Optimal Local Explainer Aggregation for Interpretable Prediction on EtoBox?

Optimal Local Explainer Aggregation for Interpretable Prediction by Li, Qiaomei; Cummings, Rachel; Mintz, Yonatan is a scholarly article available to read on EtoBox.

What is Optimal Local Explainer Aggregation for Interpretable Prediction about?

A key challenge for decision makers when incorporating black box machine learned models into practice is being able to understand the predictions provided by these models. One proposed set of methods is training surrogate explainer models which approximate the more complex model. Explainer methods are generally classified as either local or global, depending on what portion of the data space they are purported to explain. The improved coverage of global explainers usually comes at the expense of explainer fidelity. One way of trading off the advantages of both approaches is to aggregate several local explainers into a single explainer model with improved coverage. However, the problem of aggregating these local explainers is computationally challenging, and existing methods only use heuristics to form these aggregations. In this paper we propose a local explainer aggregation method which selects local explainers using non-convex optimization. In contrast to other heuristic methods, we use an integer optimization framework to combine local explainers into a near-global aggregate explainer. Our framework allows a decision-maker to directly tradeoff coverage and fidelity of the result

Author

Li, Qiaomei; Cummings, Rachel; Mintz, Yonatan

Published

2020

Language

EN