Abstract
While machine learning (ML) models are increasingly used due to their high predictive power, their use in understanding the data-generating process (DGP) is limited. Understanding the DGP requires insights into feature-target associations, which many ML models cannot directly provide due to their opaque internal mechanisms. Feature importance (FI) methods provide useful insights into the DGP under certain conditions. Since the results of different FI methods have different interpretations, selecting the correct FI method for a concrete use case is crucial and still requires expert knowledge. This paper serves as a comprehensive guide to help understand the different interpretations of global FI methods. Through an extensive review of FI methods and providing new proofs regarding their interpretation, we facilitate a thorough understanding of these methods and formulate concrete recommendations for scientific inference. We conclude by discussing options for FI uncertainty estimation and point to directions for future research aiming at full statistical inference from black-box ML models.
Original language | English |
---|---|
Title of host publication | Explainable Artificial Intelligence - Second World Conference, xAI 2024, Proceedings |
Editors | Luca Longo, Sebastian Lapuschkin, Christin Seifert |
Number of pages | 25 |
Publisher | Springer |
Publication date | 2024 |
Pages | 440-464 |
ISBN (Print) | 9783031637964 |
DOIs | |
Publication status | Published - 2024 |
Event | 2nd World Conference on Explainable Artificial Intelligence, xAI 2024 - Valletta, Malta Duration: 17 Jul 2024 → 19 Jul 2024 |
Conference
Conference | 2nd World Conference on Explainable Artificial Intelligence, xAI 2024 |
---|---|
Country/Territory | Malta |
City | Valletta |
Period | 17/07/2024 → 19/07/2024 |
Series | Communications in Computer and Information Science |
---|---|
Volume | 2154 CCIS |
ISSN | 1865-0929 |
Bibliographical note
Funding Information:MNW was supported by the German Research Foundation (DFG), Grant Numbers: 437611051, 459360854. GK was supported by the German Research Foundation through the Cluster of Excellence \u201CMachine Learning - New Perspectives for Science\u201D (EXC 2064/1 number 390727645).
Publisher Copyright:
© The Author(s) 2024.
Keywords
- Feature Importance
- Interpretable ML
- Model-agnostic Interpretability