Local Explanations via Necessity and Sufficiency: Unifying Theory and Practice
This work addresses the problem of inconsistent and underdeveloped explanations in XAI for researchers and practitioners, offering a foundational theory that could standardize the field.
The paper tackles the lack of theoretical foundations in explainable AI (XAI) by establishing necessity and sufficiency as central concepts, unifying disparate methods into a formal framework, and provides an algorithm that shows competitive performance on various tasks.
Necessity and sufficiency are the building blocks of all successful explanations. Yet despite their importance, these notions have been conceptually underdeveloped and inconsistently applied in explainable artificial intelligence (XAI), a fast-growing research area that is so far lacking in firm theoretical foundations. Building on work in logic, probability, and causality, we establish the central role of necessity and sufficiency in XAI, unifying seemingly disparate methods in a single formal framework. We provide a sound and complete algorithm for computing explanatory factors with respect to a given context, and demonstrate its flexibility and competitive performance against state of the art alternatives on various tasks.