On Understanding the Influence of Controllable Factors with a Feature Attribution Algorithm: a Medical Case Study

TL;DR

This paper introduces CAFA, a feature attribution method that distinguishes controllable from uncontrollable features, improving interpretability in datasets like COVID-19 control measures by isolating controllable factors.

Contribution

The paper proposes the CAFA approach to partition features into controllable and uncontrollable, enhancing feature attribution explanations in datasets with such distinctions.

Findings

CAFA effectively isolates controllable feature influences.

CAFA improves interpretability in COVID-19 control measures data.

Experimental results confirm CAFA's ability to exclude uncontrollable influences.

Abstract

Feature attribution XAI algorithms enable their users to gain insight into the underlying patterns of large datasets through their feature importance calculation. Existing feature attribution algorithms treat all features in a dataset homogeneously, which may lead to misinterpretation of consequences of changing feature values. In this work, we consider partitioning features into controllable and uncontrollable parts and propose the Controllable fActor Feature Attribution (CAFA) approach to compute the relative importance of controllable features. We carried out experiments applying CAFA to two existing datasets and our own COVID-19 non-pharmaceutical control measures dataset. Experimental results show that with CAFA, we are able to exclude influences from uncontrollable features in our explanation while keeping the full dataset for prediction.