Provable concept learning for interpretable predictions using variational autoencoders

Code

• github.com/nickruggeri/clap-interpretable-predictions
  OfficialIn paperpytorch★ 15
• github.com/nikruggeri/clap-interpretable-predictions
  OfficialIn paperpytorch★ 15

Abstract

In safety-critical applications, practitioners are reluctant to trust neural networks when no interpretable explanations are available. Many attempts to provide such explanations revolve around pixel-based attributions or use previously known concepts. In this paper we aim to provide explanations by provably identifying high-level, previously unknown ground-truth concepts. To this end, we propose a probabilistic modeling framework to derive (C)oncept (L)earning and (P)rediction (CLAP) -- a VAE-based classifier that uses visually interpretable concepts as predictors for a simple classifier. Assuming a generative model for the ground-truth concepts, we prove that CLAP is able to identify them while attaining optimal classification accuracy. Our experiments on synthetic datasets verify that CLAP identifies distinct ground-truth concepts on synthetic datasets and yields promising results on the medical Chest X-Ray dataset.

Tasks

Reproductions