TreeView: Peeking into Deep Neural Networks Via Feature-Space Partitioning
This addresses the need for trustworthy explanations in opaque deep learning models, though it appears incremental as it builds on existing interpretability approaches.
The paper tackles the problem of interpreting deep neural networks without sacrificing accuracy by proposing TreeView, a method that builds a hierarchical representation through feature-space partitioning to reveal how models iteratively reject unlikely class labels.
With the advent of highly predictive but opaque deep learning models, it has become more important than ever to understand and explain the predictions of such models. Existing approaches define interpretability as the inverse of complexity and achieve interpretability at the cost of accuracy. This introduces a risk of producing interpretable but misleading explanations. As humans, we are prone to engage in this kind of behavior \cite{mythos}. In this paper, we take a step in the direction of tackling the problem of interpretability without compromising the model accuracy. We propose to build a Treeview representation of the complex model via hierarchical partitioning of the feature space, which reveals the iterative rejection of unlikely class labels until the correct association is predicted.