Interface description

XAIBase.jl is a light-weight dependency that defines the interface of XAI methods in the Julia-XAI ecosystem.

Building on top of XAIBase (or providing an interface via package extensions) makes your package compatible with the Julia-XAI ecosystem, allowing you to automatically compute heatmaps for vision and language models using VisionHeatmaps.jl and TextHeatmaps.jl.

This only requires you to fulfill the following two requirements:

1. An XAI method has to be a subtype of AbstractXAIMethod
2. An XAI algorithm has to implement a call_analyzer method:

import XAIBase: call_analyzer

call_analyzer(input, method::MyMethod, output_selector::AbstractOutputSelector; kwargs...)

• call_analyzer has to return an Explanation
• The input is expected to have a batch dimensions as its last dimension
• When applied to a batch, the method returns a single Explanation, which contains the batched output in the val field.
• AbstractOutputSelectors are predefined callable structs that select a single scalar value from a model's output, e.g. the maximally activated output of a classifier using MaxActivationSelector or a specific output using IndexSelector.

Refer to the Explanation documentation for a description of the expected fields. For more information, take a look at src/XAIBase.jl.

Implementation template

Julia-XAI methods will usually follow the following template:

using XAIBase
import XAIBase: call_analyzer

struct MyMethod{M} <: AbstractXAIMethod 
    model::M    
end

function call_analyzer(input, method::MyMethod, output_selector::AbstractOutputSelector; kwargs...)
    output = method.model(input)
    output_selection = output_selector(output)

    val = ...         # your method's implementation
    extras = nothing  # optionally add additional information using a named tuple
    return Explanation(val, input, output, output_selection, :MyMethod, :attribution, extras)
end

Refer to the example implementations for more information.