Sökning: onr:"swepub:oai:DiVA.org:mdh-64913" >
Investigating Addit...
Investigating Additive Feature Attribution for Regression
-
- Islam, Mir Riyanul, Doctoral Student, 1991- (författare)
- Mälardalens universitet,Akademin för innovation, design och teknik
-
- Weber, Rosina O. (författare)
- Drexel University, United States
-
- Ahmed, Mobyen Uddin, Dr, 1976- (författare)
- Mälardalens universitet,Inbyggda system
-
visa fler...
-
- Begum, Shahina, 1977- (författare)
- Mälardalens universitet,Inbyggda system
-
visa färre...
-
(creator_code:org_t)
- 2023
- Engelska.
- Relaterad länk:
-
https://urn.kb.se/re...
Abstract
Ämnesord
Stäng
- Feature attribution is a class of explainable artificial intelligence (XAI) methods that produce the contributions of data features to a model's decision. There are multiple accounts stating that feature attribution methods produce inconsistent results and should always be evaluated. However, the existing body of literature on evaluation techniques is still immature with multiple proposed techniques and a lack of widely adopted methods, making it difficult to recognize the best approach for each circumstance. This article investigates an approach to creating synthetic data for regression that can be used to evaluate the results of feature attribution methods. From a real-world dataset, the proposed approach describes how to create synthetic data that preserves the patterns of the original data and enables comprehensive evaluation of XAI methods. This research also demonstrates how global and local feature attributions can be represented in the additive form of case-based reasoning as a benchmark method for evaluation. Finally, this work demonstrates the case where a method that includes a standardization step does not produce feature attributions of the same quality as one that does not use standardization in the context of a regression task.
Ämnesord
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Sciences (hsv//eng)
Nyckelord
- Explainability
- Additive Feature Attribution
- Regression
- Additive CBR
- CBR
- Evaluation
- Interpretability
- LIME
- SHAP
- Synthetic Data
- XAI.
Publikations- och innehållstyp
- vet (ämneskategori)
- ovr (ämneskategori)