DeepAI
Log In Sign Up

Do Concept Bottleneck Models Learn as Intended?

05/10/2021
by   Andrei Margeloiu, et al.
0

Concept bottleneck models map from raw inputs to concepts, and then from concepts to targets. Such models aim to incorporate pre-specified, high-level concepts into the learning procedure, and have been motivated to meet three desiderata: interpretability, predictability, and intervenability. However, we find that concept bottleneck models struggle to meet these goals. Using post hoc interpretability methods, we demonstrate that concepts do not correspond to anything semantically meaningful in input space, thus calling into question the usefulness of concept bottleneck models in their current form.

READ FULL TEXT

page 1

page 2

page 3

page 4

05/31/2022

Post-hoc Concept Bottleneck Models

Concept Bottleneck Models (CBMs) map the inputs onto a set of interpreta...
07/09/2020

Concept Bottleneck Models

We seek to learn models that we can interact with using high-level conce...
09/19/2022

Concept Embedding Models

Deploying AI-powered systems requires trustworthy models supporting effe...
05/31/2022

GlanceNets: Interpretabile, Leak-proof Concept-based Models

There is growing interest in concept-based models (CBMs) that combine hi...
11/07/2022

Towards learning to explain with concept bottleneck models: mitigating information leakage

Concept bottleneck models perform classification by first predicting whi...
11/21/2022

Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification

Concept Bottleneck Models (CBM) are inherently interpretable models that...