Conditional Feature Importance

Implementation of CFI using modular sampling approach

References

Blesch K, Koenen N, Kapar J, Golchian P, Burk L, Loecher M, Wright M (2025). “Conditional Feature Importance with Generative Modeling Using Adversarial Random Forests.” Proceedings of the AAAI Conference on Artificial Intelligence, 39(15), 15596–15604. doi:10.1609/aaai.v39i15.33712 .

Super classes

xplainfi::FeatureImportanceMethod -> xplainfi::PerturbationImportance -> CFI

Methods

Public methods

• CFI$new()

• CFI$compute()

• CFI$clone()

Inherited methods

• xplainfi::FeatureImportanceMethod$obs_loss()
• xplainfi::FeatureImportanceMethod$print()
• xplainfi::FeatureImportanceMethod$reset()
• xplainfi::FeatureImportanceMethod$scores()
• xplainfi::PerturbationImportance$importance()

---

Method new()

Creates a new instance of the CFI class

Usage

CFI$new(
  task,
  learner,
  measure = NULL,
  resampling = NULL,
  features = NULL,
  groups = NULL,
  relation = "difference",
  n_repeats = 1L,
  batch_size = NULL,
  sampler = NULL
)

Arguments

task, learner, measure, resampling, features, groups, relation, n_repeats, batch_size

Passed to PerturbationImportance.

sampler

(ConditionalSampler) Optional custom sampler. Defaults to instantiating ConditionalARFSampler internally with default parameters.

---

Method compute()

Compute CFI scores

Usage

CFI$compute(
  n_repeats = NULL,
  batch_size = NULL,
  store_models = TRUE,
  store_backends = TRUE
)

Arguments

n_repeats

(integer(1)) Number of permutation iterations. If NULL, uses stored value.

batch_size

(integer(1) | NULL: NULL) Maximum number of rows to predict at once. If NULL, uses stored value.

store_models, store_backends

(logical(1): TRUE) Whether to store fitted models / data backends, passed to mlr3::resample internally for the initial fit of the learner. This may be required for certain measures and is recommended to leave enabled unless really necessary.

---

Method clone()

The objects of this class are cloneable with this method.

Usage

CFI$clone(deep = FALSE)

Arguments

deep

Whether to make a deep clone.

Examples

library(mlr3)
library(mlr3learners)

task <- sim_dgp_correlated(n = 500)

# Using default ConditionalARFSampler
cfi <- CFI$new(
  task = task,
  learner = lrn("regr.ranger", num.trees = 10),
  measure = msr("regr.mse")
)
#> ℹ No `sampler` provided, using <ConditionalARFSampler> with default settings.
#> ℹ No <Resampling> provided, using `resampling = rsmp("holdout", ratio = 2/3)`
#>   (test set size: 167)
cfi$compute()
cfi$importance()
#> Key: <feature>
#>    feature  importance
#>     <char>       <num>
#> 1:      x1 2.985885240
#> 2:      x2 0.171542034
#> 3:      x3 1.525342471
#> 4:      x4 0.005701918