Causality-Inspired Taxonomy for Explainable Artificial Intelligence
This work provides a taxonomy for xAI that could help researchers develop more complete explainability methods, though it appears incremental as it builds on existing causality and xAI concepts.
The authors tackled the problem of unifying causality and explainable AI (xAI) by proposing a causality-inspired framework for xAI, applying it to analyze 81 research papers on biometrics as a case study.
As two sides of the same coin, causality and explainable artificial intelligence (xAI) were initially proposed and developed with different goals. However, the latter can only be complete when seen through the lens of the causality framework. As such, we propose a novel causality-inspired framework for xAI that creates an environment for the development of xAI approaches. To show its applicability, biometrics was used as case study. For this, we have analysed 81 research papers on a myriad of biometric modalities and different tasks. We have categorised each of these methods according to our novel xAI Ladder and discussed the future directions of the field.