Knowledge graphs for empirical concept retrieval

arXiv:2404.07008v1 Announce Type: new
Abstract: Concept-based explainable AI is promising as a tool to improve the understanding of complex models at the premises of a given user, viz.\ as a tool for personalized explainability. An important class of concept-based explainability methods is constructed with empirically defined concepts, indirectly defined through a set of positive and negative examples, as in the TCAV approach (Kim et al., 2018). While it is appealing to the user to avoid formal definitions of concepts and …

abstract arxiv class concept concepts cs.ai cs.lg explainability explainable ai graphs knowledge knowledge graphs personalized positive retrieval set through tool type understanding viz