2019/09/04 by John Merrill, Geoff Ward, Merrill, John +7 · 1 citation
Computer Science · Decision Sciences · #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #H.1.2 #I.2.6 #K.4 #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Data Classification #Scientific Computing and Data Management
paper · pdf · doi:10.48550/arxiv.1909.01869
openalex publication_date 2019/09/04 · openalex created_date 2019/09/12 · openalex updated_date 2026/07/28
We introduce Generalized Integrated Gradients (GIG), a formal extension of the Integrated Gradients (IG) (Sundararajan et al., 2017) method for attributing credit to the input variables of a predictive model. GIG improves IG by explaining a broader variety of functions that arise from practical applications of ML in domains like financial services. GIG is constructed to overcome limitations of Shapley (1953) and Aumann-Shapley (1974), and has desirable properties when compared to other approaches. We prove GIG is the only correct method, under a small set of reasonable axioms, for providing explanations for mixed-type models or games. We describe the implementation, and present results of experiments on several datasets and systems of models.