Jump to Content

Towards Automatic Concept-based Explanations

Amirata Ghorbani
James Zou
Been Kim
NeurIPS (2019)


Interpretability has become an important topic of research as more machine learning (ML) models are deployed and widely used to make important decisions. Most of the current explanation methods provide explanations through feature importance scores, which identify features that are salient for each individual input. However, how to systematically summarize and interpret such per sample feature importance scores itself is challenging. In this work, we propose principles and desiderata for \emph{concept} based explanation, which goes beyond per-sample features to identify higher level human-understandable concepts that apply across the entire dataset. We develop a new algorithm, ACE, to automatically extract visual concepts. Our systematic experiments demonstrate that ACE discovers concepts that are human-meaningful, coherent and salient for the neural network's predictions.