Conceptual Learning via Embedding Approximations for Reinforcing Interpretability and Transparency

TL;DR

This paper introduces CLEAR, a framework that enhances interpretability in concept bottleneck models by approximating concept embeddings in a latent space, leading to improved transparency and state-of-the-art performance in image classification.

Contribution

CLEAR leverages score matching and Langevin sampling to approximate concept embeddings, enabling better interpretability and selection of concepts in vision-language models.

Findings

Achieved state-of-the-art results on multiple benchmarks.

Provided more transparent decision-making insights.

Improved concept selection process in CBMs.

Abstract

Concept bottleneck models (CBMs) have emerged as critical tools in domains where interpretability is paramount. These models rely on predefined textual descriptions, referred to as concepts, to inform their decision-making process and offer more accurate reasoning. As a result, the selection of concepts used in the model is of utmost significance. This study proposes \underline{\textbf{C}}onceptual \underline{\textbf{L}}earning via \underline{\textbf{E}}mbedding \underline{\textbf{A}}pproximations for \underline{\textbf{R}}einforcing Interpretability and Transparency, abbreviated as CLEAR, a framework for constructing a CBM for image classification. Using score matching and Langevin sampling, we approximate the embedding of concepts within the latent space of a vision-language model (VLM) by learning the scores associated with the joint distribution of images and concepts. A concept selection process is then employed to optimize the similarity between the learned embeddings and the predefined ones. The derived bottleneck offers insights into the CBM's decision-making process, enabling more comprehensive interpretations. Our approach was evaluated through extensive experiments and achieved state-of-the-art performance on various benchmarks. The code for our experiments is available at https://github.com/clearProject/CLEAR/tree/main