On Understanding the Influence of Controllable Factors with a Feature Attribution Algorithm: a Medical Case Study
16th International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2022
; 2022.
Article
in English
| Scopus | ID: covidwho-2078231
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. © 2022 IEEE.
Full text:
Available
Collection:
Databases of international organizations
Database:
Scopus
Type of study:
Case report
Language:
English
Journal:
16th International Conference on INnovations in Intelligent SysTems and Applications, INISTA 2022
Year:
2022
Document Type:
Article
Similar
MEDLINE
...
LILACS
LIS