What type of study is this?

This is a Literature Review study.

September 5, 2025Open Access

Feature attribution methods in machine learning: a state-of-the-art review

Puntos clave

Feature attribution techniques provide insights into machine learning models, enhancing explainability.
A comparative analysis reveals trade-offs between model-agnostic methods' broad applicability and model-specific methods' efficiency.
Model-agnostic techniques can have higher computational costs while offering universal applicability across different models.
Model-specific methods can lead to more effective explanations using internal model features, though with reduced generality.

Resumen

This paper presents a state-of-the-art survey of feature attribution techniques employed in explainable AI. We organize the existing literature into a proposed taxonomy of model-agnostic and model-specific approaches. We analyze the formal definitions, mathematical formulations, usage contexts, strengths, and limitations of these methods. A comparative analysis highlights key trade-offs concerning model agnosticism, explanation form, computational cost, and fidelity to the model. We find that while model-agnostic techniques offer broad applicability by treating models as oracles, often at a higher computational cost, model-specific methods leverage internal model architecture or gradients for potentially more efficient and faithful explanations, albeit with reduced generality.

Leer artículo completoexternamente

Me gusta

Guardar

Ver artículo completo