Get our free extension to see links to code for papers anywhere online!Free add-on: code for papers everywhere!Free add-on: See code for papers anywhere!

Add to Chrome

Add to Firefox

Add to Edge

Carina Schnuck

Provable concept learning for interpretable predictions using variational inference

Apr 01, 2022
Armeen Taeb, Nicolo Ruggeri, Carina Schnuck, Fanny Yang

Figure 1 for Provable concept learning for interpretable predictions using variational inference

Figure 2 for Provable concept learning for interpretable predictions using variational inference

Figure 3 for Provable concept learning for interpretable predictions using variational inference

Figure 4 for Provable concept learning for interpretable predictions using variational inference

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 level attributions or use previously known concepts. In this paper we aim to provide explanations by provably identifying \emph{high-level, previously unknown 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 linear predictors. Assuming that the data generating mechanism involves predictive concepts, we prove that our method is able to identify them while attaining optimal classification accuracy. We use synthetic experiments for validation, and also show that on real-world (PlantVillage and ChestXRay) datasets, CLAP effectively discovers interpretable factors for classifying diseases.

Via

Access Paper or Ask Questions