Concept Embedding Models

by   Mateo Espinosa Zarlenga, et al.

Deploying AI-powered systems requires trustworthy models supporting effective human interactions, going beyond raw prediction accuracy. Concept bottleneck models promote trustworthiness by conditioning classification tasks on an intermediate level of human-like concepts. This enables human interventions which can correct mispredicted concepts to improve the model's performance. However, existing concept bottleneck models are unable to find optimal compromises between high task accuracy, robust concept-based explanations, and effective interventions on concepts – particularly in real-world conditions where complete and accurate concept supervisions are scarce. To address this, we propose Concept Embedding Models, a novel family of concept bottleneck models which goes beyond the current accuracy-vs-interpretability trade-off by learning interpretable high-dimensional concept representations. Our experiments demonstrate that Concept Embedding Models (1) attain better or competitive task accuracy w.r.t. standard neural models without concepts, (2) provide concept representations capturing meaningful semantics including and beyond their ground truth labels, (3) support test-time concept interventions whose effect in test accuracy surpasses that in standard concept bottleneck models, and (4) scale to real-world conditions where complete concept supervisions are scarce.


page 18

page 19

page 22


Learning to Intervene on Concept Bottlenecks

While traditional deep learning models often lack interpretability, conc...

Do Concept Bottleneck Models Learn as Intended?

Concept bottleneck models map from raw inputs to concepts, and then from...

Post-hoc Concept Bottleneck Models

Concept Bottleneck Models (CBMs) map the inputs onto a set of interpreta...

Selective Concept Models: Permitting Stakeholder Customisation at Test-Time

Concept-based models perform prediction using a set of concepts that are...

Human Uncertainty in Concept-Based AI Systems

Placing a human in the loop may abate the risks of deploying AI systems ...

Towards Robust Metrics for Concept Representation Evaluation

Recent work on interpretability has focused on concept-based explanation...

Interpretable Neural-Symbolic Concept Reasoning

Deep learning methods are highly accurate, yet their opaque decision pro...

Please sign up or login with your details

Forgot password? Click here to reset