Explainability

Surrogate Models

Techniques that approximate complex models with interpretable ones

3 subcategories • 5 techniques

Approximates entire model behaviour with simpler model (e.g., GAMs)

Approximates model behaviour around specific instances (e.g., LIME)

Extracts interpretable rules from complex models (e.g., ANCHOR, RuleFit)

Techniques

5 techniques

		Models	Data Types	Description
Local Interpretable Model-Agnostic Explanations	Algorithmic	Architecture/model Agnostic Requirements/black Box	Any	LIME (Local Interpretable Model-agnostic Explanations) explains individual predictions by approximating the complex...
Ridge Regression Surrogates	Algorithmic	Architecture/model Agnostic Requirements/black Box	Tabular	A ridge regression surrogate approximates a complex model with a linear equation fitted to the complex model's own...
RuleFit	Algorithmic	Architecture/model Agnostic Paradigm/supervised +1	Tabular	RuleFit builds a predictive model that a person can read: a short list of if-then rules plus a few ordinary feature...
Generalized Additive Models	Algorithmic	Architecture/linear Models/gam Paradigm/parametric +2	Tabular	A generalised additive model (GAM) builds its prediction by adding a baseline and one smooth curve for each input...
ANCHOR	Algorithmic	Architecture/model Agnostic Requirements/black Box	Tabular	ANCHOR explains one prediction of a black-box classifier with an if-then rule, called an anchor, such as 'age > 30 AND...

Rows per page

Page 1 of 1