Title
Markov-Boundary Consistent Feature Attribution
Authors
[ 1 ] Wydział Informatyki i Telekomunikacji, Politechnika Poznańska | [ 2 ] Instytut Informatyki, Wydział Informatyki i Telekomunikacji, Politechnika Poznańska | [ SzD ] doctoral school student | [ P ] employee
Scientific discipline (Law 2.0)
Year of publication
2025
Chapter type
chapter in monograph / paper
Publication language
english
Keywords
EN
- causality
- explainability
Abstract
EN Feature attribution methods aim to explain the predictions of machine learning models by assigning importance scores to input features. Recent work has highlighted the importance of developing attribution methods that respect causal structures. Furthermore, they showed that existing approaches can assign significant importance to variables outside the Markov boundary, even though these variables provide no additional predictive information when the Markov boundary is observed. To address these limitations we design a new attribution method that accounts for both predictive power and causal structure of the features. Our method does not assume access to the structure and achieves balanced attributions using properly defined characteristic function. We show that our method provably assigns high attributions to the variables in the Markov boundary and experimentally evaluate it in a fairness inspired setting.
Comments
Scaling Up Intervention Models (SIM) Workshop
License type
CC BY (attribution alone)
Open Access Mode
publisher's website
Open Access Text Version
final published version
Date of Open Access to the publication
at the time of publication
Ministry points / chapter
5
Ministry points / conference (CORE)
200
System created by Poznań University of Technology
and Poznan Supercomputing and Networking Center
Log in through eKonto to add to SIS