Causality for Inherently Explainable Transformers: CAT-XPLAIN. (arXiv:2206.14841v1 [cs.CV])

There have been several post-hoc explanation approaches developed to explain
pre-trained black-box neural networks. However, there is still a gap in
research efforts toward designing neural networks that are inherently
explainable. In this paper, we utilize a recently proposed instance-wise
post-hoc causal explanation method to make an existing transformer architecture
inherently explainable. Once trained, our model provides an explanation in the
form of top-$k$ regions in the input space of the given instance contributing
to its decision. We evaluate our method on binary classification tasks using
three image datasets: MNIST, FMNIST, and CIFAR. Our results demonstrate that
compared to the causality-based post-hoc explainer model, our inherently
explainable model achieves better explainability results while eliminating the
need of training a separate explainer model. Our code is available at



Related post