Feature Importance versus Feature Influence and What It Signifies for Explainable AI

Kary Främling*

*Tämän työn vastaava kirjoittaja

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussaConference article in proceedingsScientificvertaisarvioitu

Abstrakti

When used in the context of decision theory, feature importance expresses how much changing the value of a feature can change the model outcome (or the utility of the outcome), compared to other features. Feature importance should not be confused with the feature influence used by most state-of-the-art post-hoc Explainable AI methods. Contrary to feature importance, feature influence is measured against a reference level or baseline. The Contextual Importance and Utility (CIU) method provides a unified definition of global and local feature importance that is applicable also for post-hoc explanations, where the value utility concept provides instance-level assessment of how favorable or not a feature value is for the outcome. The paper shows how CIU can be applied to both global and local explainability, assesses the fidelity and stability of different methods, and shows how explanations that use contextual importance and contextual utility can provide more expressive and flexible explanations than when using influence only.

AlkuperäiskieliEnglanti
OtsikkoExplainable Artificial Intelligence - 1st World Conference, xAI 2023, 2023, Proceedings
ToimittajatLuca Longo
KustantajaSpringer
Sivut241-259
Sivumäärä19
ISBN (painettu)978-3-031-44063-2
DOI - pysyväislinkit
TilaJulkaistu - 2023
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisussa
TapahtumaWorld Conference on eXplainable Artificial Intelligence - Lisbon, Portugali
Kesto: 26 heinäk. 202328 heinäk. 2023
Konferenssinumero: 1

Julkaisusarja

NimiCommunications in Computer and Information Science
Vuosikerta1901 CCIS
ISSN (painettu)1865-0929
ISSN (elektroninen)1865-0937

Conference

ConferenceWorld Conference on eXplainable Artificial Intelligence
LyhennettäxAI
Maa/AluePortugali
KaupunkiLisbon
Ajanjakso26/07/202328/07/2023

Sormenjälki

Sukella tutkimusaiheisiin 'Feature Importance versus Feature Influence and What It Signifies for Explainable AI'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä