Poster
Towards Automatic Concept-based Explanations
Amirata Ghorbani · James Wexler · James Zou · Been Kim

Thu Dec 12th 10:45 AM -- 12:45 PM @ East Exhibition Hall B + C #86
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 important 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 \alg discovers concepts that are human-meaningful, coherent and important for the neural network's predictions.

Author Information

Amirata Ghorbani (Stanford University)
James Wexler
James Zou (Stanford University)
Been Kim (Google)

More from the Same Authors