Towards the Linear Algebra Based Taxonomy of XAI Explanations
This work addresses the need for a mathematical framework in XAI taxonomy, though it is incremental as it builds on existing taxonomies by focusing on linear algebra for specific data types.
The paper tackles the problem of mathematically distinguishing and comparing explanations in explainable AI by proposing a linear algebra-based taxonomy for local explanations when data is in ℝⁿ, providing a more structured alternative to human-centric taxonomies.
This paper proposes an alternative approach to the basic taxonomy of explanations produced by explainable artificial intelligence techniques. Methods of Explainable Artificial Intelligence (XAI) were developed to answer the question why a certain prediction or estimation was made, preferably in terms easy to understand by the human agent. XAI taxonomies proposed in the literature mainly concentrate their attention on distinguishing explanations with respect to involving the human agent, which makes it complicated to provide a more mathematical approach to distinguish and compare different explanations. This paper narrows its attention to the cases where the data set of interest belongs to $\mathbb{R} ^n$ and proposes a simple linear algebra-based taxonomy for local explanations.