Towards Better Generalization and Interpretability in Unsupervised Concept-Based Models

TL;DR

This paper presents LCBM, an unsupervised concept-based image classification model that improves generalization and interpretability by modeling concepts as Bernoulli variables, requiring less supervision and aligning better with human understanding.

Contribution

Introduces LCBM, a novel unsupervised concept-based model that enhances generalization and interpretability with fewer concepts and better human-aligned representations.

Findings

LCBM surpasses existing models in generalization.

LCBM nearly matches black-box model performance.

Discovered concepts are more intuitive for humans.

Abstract

To increase the trustworthiness of deep neural networks, it is critical to improve the understanding of how they make decisions. This paper introduces a novel unsupervised concept-based model for image classification, named Learnable Concept-Based Model (LCBM) which models concepts as random variables within a Bernoulli latent space. Unlike traditional methods that either require extensive human supervision or suffer from limited scalability, our approach employs a reduced number of concepts without sacrificing performance. We demonstrate that LCBM surpasses existing unsupervised concept-based models in generalization capability and nearly matches the performance of black-box models. The proposed concept representation enhances information retention and aligns more closely with human understanding. A user study demonstrates the discovered concepts are also more intuitive for humans to interpret. Finally, despite the use of concept embeddings, we maintain model interpretability by means of a local linear combination of concepts.