Skip to main content

Local Interpretation (LIME)

Synopsis​

This operator is a meta operator to generate an approximation of the decision a given (complex) model made for specific examples. The key idea is to generate local feature weights (

Interpretations) which can be easier interpreted and thus can help to understand the reasoning for a decision of a complex model on a per example basis.

Description​

To do this we run the following algorithm:

    1. Draw uniformly distributed random data in [0,1] for all attributes
    1. Scale them to the same min/max like the input data
    1. Score them with the complex model

  • For each example in your input set do:

    1. Calculate the Euclidean distance d between the example and your random examples (normalized)
    1. Use w = sqrt(exp(-(pow(d,2)/pow(this.kernel_width,2))) as a weight for the local model
    1. Run the inner process, which creates a feature weight (e.g. via Weight by XXX, Linear Regression or Logistic Regression)
    1. Add the top k attributes with their importance to the input set

As a result you get example set with new attributes describing the most important local attributes and a collection of attribute weights containing the full vector. If you calculate a performance vector in the inner process and connect it to the Per port, you can get the performance of the local description attached to every example.

Input​

exa​

The ExampleSet you want to get interpretations for. Needs to have a reasonable size to estimate min and max.

mod​

The (complex) input model.

Output​

exa​

ExampleSet with local interpretations.

mod​

The passed through input model.

wei​

A collection of Attribute Weights for each example.

loc​

The collection of local models.

Parameters​

Use locality heuristics​

If this parameter is set to true the locality heuristics derived from LIME (0.2*sqrt(#atts)) is used, otherwise the locality has to be set manually.

Locality​

A factor describing how local the model should be. The smaller this value is the more localized the model. It is used as kernel_width in step 5.

Sample size​

Number of random examples drawn to build the local models on.

Number of attributes​

Number of attributes put into the ExampleSet in step 7. All attribute weights are delivered via the 'wei' port.

Weight threshold​

A threshold to remove all examples with weights smaller than this value in each iteration. This removes irrelevant (non-local) random examples from the learning and can significantly speed up the operator.

Use local random seed​

This parameter indicates if a local random seed should be used.

Local random seed​

If the use local random seed parameter is checked this parameter determines the local random seed.

See Also​