Generative causal explanations of black-box classifiers

By Matthew R. O'Shaughnessy, Gregory H. Canal, Marissa Connor, Mark A. Davenport, Christopher J. Rozell. 2020

83 citations recorded by the source corpus.

We develop a method for generating causal post-hoc explanations of black-box classifiers based on a learned low-dimensional representation of the data. The explanation is causal in the sense that changing learned latent factors produces a change in the classifier output statistics. To construct these explanations, we design a learning framework that leverages a generative model and information-theoretic measures of causal influence. Our objective function encourages both the generative model to faithfully represent the data distribution and the latent factors to have a large causal influence on the classifier output. Our method learns both global and local explanations, is compatible with any classifier that admits class probabilities and a gradient, and does not require labeled attributes or knowledge of causal structure. Using carefully controlled test cases, we provide intuition that illuminates the function of our causal objective. We then demonstrate the practical utility of our method on image recognition tasks.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Concept Bottleneck Models (2020, background): “See, e.g., Goyal et al. (2019); O’Shaughnessy et al. (2020) for discussions on causality in the context of interpreting models with concepts.”
Proactive Pseudo-Intervention: Causally Informed Contrastive Learning For Interpretable Vision Models (2020, background): “Such post hoc causal explanations can be generated with black-box classiﬁers based on a learned low-dimensional representation of the data [41] .”
Explaining in Style: Training a GAN to explain a classifier in StyleSpace (2021, methodology): “The closest method in spirit to the explanations provided by our StylEx approach is [20], though their method only works on small images, and Figure 3.”