Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)

• DOI: 10.48550/arxiv.1711.11279
• Publication Date: 2017-01-01
• Authors: Kim, Been; Wattenberg, Martin; Gilmer, Justin; Cai, Carrie; Wexler, James; Viegas, Fernanda; Sayres, Rory
• Keywords: FOS: Computer and information sciences; Statistics - Machine Learning; 0202 electrical engineering, electronic engineering, information engineering; Machine Learning (stat.ML); 02 engineering and technology

The interpretation of deep learning models is a challenge due to their size, complexity, and often opaque internal state. In addition, many systems, such as image classifiers, operate on low-level features rather than high-level concepts. To address these challenges, we introduce Concept Activation Vectors (CAVs), which provide an interpretation of a neural net's internal state in terms of human-friendly concepts. The key idea is to view the high-dimensional internal state of a neural net as an aid, not an obstacle. We show how to use CAVs as part of a technique, Testing with CAVs (TCAV), that uses directional derivatives to quantify the degree to which a user-defined concept is important to a classification result--for example, how sensitive a prediction of "zebra" is to the presence of stripes. Using the domain of image classification as a testing ground, we describe how CAVs may be used to explore hypotheses and generate insights for a standard image classification network as well as a medical application.