CCW-Net Uses Interventional Mediation Analysis for Causal Concept Explanations
Researchers introduce Causal Concept Wrapper Network (CCW-Net), which uses interventional mediation analysis as a training objective to align concept-based explanations with model outputs. The method targets necessity, sufficiency, and independence of concept representations through counterfactual concept representations. Mediation analysis is also proposed as an evaluation tool to quantify how much model output is causally attributable to each concept label combination. The approach is evaluated in aircraft control, driving, and image classification settings.