EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

A survey of feature attribution techniques in explainable AI: taxonomy, analysis and comparison

Mohd Amril Nazir, Edmund Evangelista, Syed M Salman Bukhari, Ravishankar Sharma

Annals of Mathematics and Computer Science · 03.06.2025 · 28 · 115-126

DOI: 10.56947/amcs.v28.547 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Annals of Mathematics and Computer Science, online erschienen am 03.06.2025. Verfasst von Mohd Amril Nazir und 3 weiteren Autor:innen. Die Arbeit wurde bisher 13-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The feature attribution methods have become central to explainable artificial intelligence (XAI), providing critical insights into how machine learning (ML) models make individual and aggregate decisions. This survey presents a complete taxonomy of feature attribution techniques, organizing them into model-agnostic and model-specific categories while highlighting extensions such as rule-based and attention-based explanations. We analyze formal definitions of each method, mathematical formulations, application contexts, strengths, and limitations. A comparative analysis highlights key trade-offs among model flexibility, computational cost, explanation fidelity, and interpretability. In addition to theoretical perspectives, we provide practical comparisons of selected methods on benchmark tasks to guide real-world applicability. The emerging trends toward global interpretability, hybrid attribution approaches, and human-centered evaluation frameworks are discussed. This survey synthesizes current advancements and presents future directions for developing scalable, robust, and user-aligned feature attribution methods to advance responsible and transparent AI.

Zitieren

APA

Nazir, M. A., Evangelista, E., Bukhari, S. M. S., & Sharma, R. (2025). A survey of feature attribution techniques in explainable AI: taxonomy, analysis and comparison. Annals of Mathematics and Computer Science, 28, 115-126. https://doi.org/10.56947/amcs.v28.547

Vancouver

Nazir MA, Evangelista E, Bukhari SMS, Sharma R. A survey of feature attribution techniques in explainable AI: taxonomy, analysis and comparison. Annals of Mathematics and Computer Science. 2025;28:115-126. doi:10.56947/amcs.v28.547

BibTeX
@article{Nazir2025,
  author = {Nazir, Mohd Amril and Evangelista, Edmund and Bukhari, Syed M Salman and Sharma, Ravishankar},
  title = {A survey of feature attribution techniques in explainable AI: taxonomy, analysis and comparison},
  journal = {Annals of Mathematics and Computer Science},
  year = {2025},
  volume = {28},
  pages = {115--126},
  doi = {10.56947/amcs.v28.547}
}
Kostenlos starten →