Towards a Unified Evaluation of Explanation Methods without Ground Truth
This addresses the challenge of objective evaluation in explainable AI, but it is incremental as it builds on existing methods without introducing a new paradigm.
The paper tackles the problem of evaluating explanation methods for neural networks without ground-truth explanations by proposing four metrics, which are applied to nine benchmark methods to provide new insights.
This paper proposes a set of criteria to evaluate the objectiveness of explanation methods of neural networks, which is crucial for the development of explainable AI, but it also presents significant challenges. The core challenge is that people usually cannot obtain ground-truth explanations of the neural network. To this end, we design four metrics to evaluate explanation results without ground-truth explanations. Our metrics can be broadly applied to nine benchmark methods of interpreting neural networks, which provides new insights of explanation methods.