Beyond Concept Bottleneck Models: How to Make Black Boxes Intervenable?

Understand

Recently, interpretable machine learning has re-explored concept bottleneck models (CBM).

• An advantage of this model class is the user's ability to intervene on predicted concept values, affecting the downstream output.
• In this work, we introduce a method to perform such concept-based interventions on pretrained neural networks, which are not interpretable by design, only given a small validation set with concept labels.
• Furthermore, we formalise the notion of intervenability as a measure of the effectiveness of concept-based interventions and leverage this definition to fine-tune black boxes.