Explaining Classifiers with Causal Concept Effect (CaCE)
This addresses the need for more reliable explainability methods in AI, though it is incremental as it builds on existing causal and generative approaches.
The paper tackles the problem of understanding deep neural network classification decisions by introducing the Causal Concept Effect (CaCE) to avoid misleading explanations from confounding, and shows that VAE-CaCE can accurately estimate true concept causal effects in experiments on high-dimensional images.
How can we understand classification decisions made by deep neural networks? Many existing explainability methods rely solely on correlations and fail to account for confounding, which may result in potentially misleading explanations. To overcome this problem, we define the Causal Concept Effect (CaCE) as the causal effect of (the presence or absence of) a human-interpretable concept on a deep neural net's predictions. We show that the CaCE measure can avoid errors stemming from confounding. Estimating CaCE is difficult in situations where we cannot easily simulate the do-operator. To mitigate this problem, we use a generative model, specifically a Variational AutoEncoder (VAE), to measure VAE-CaCE. In an extensive experimental analysis, we show that the VAE-CaCE is able to estimate the true concept causal effect, compared to baselines for a number of datasets including high dimensional images.