Causality for Inherently Explainable Transformers: CAT-XPLAIN
This work addresses the need for inherently explainable models in machine learning, offering a practical solution for domains requiring interpretability, though it is incremental as it builds on existing methods.
The authors tackled the problem of designing inherently explainable neural networks by adapting a post-hoc causal explanation method into a transformer architecture, achieving better explainability results on binary classification tasks with MNIST, FMNIST, and CIFAR datasets compared to a separate post-hoc explainer model.
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 https://github.com/mvrl/CAT-XPLAIN.