Benchmarking and survey of explanation methods for black box models

Bodria F., Giannotti F., Guidotti R., Naretto F., Pedreschi D., Rinzivillo S.

FOS: Computer and information sciences  Artificial Intelligence (cs.AI)  Computer Science Applications  Explainable artificial intelligence  Interpretable machine learning  Information Systems  Benchmarking  Computer Networks and Communications  Computers and Society (cs.CY)  Machine Learning (cs.LG)  Transparent models 

The rise of sophisticated black-box machine learning models in Artificial Intelligence systems has prompted the need for explanation methods that reveal how these models work in an understandable way to users and decision makers. Unsurprisingly, the state-of-the-art exhibits currently a plethora of explainers providing many different types of explanations. With the aim of providing a compass for researchers and practitioners, this paper proposes a categorization of explanation methods from the perspective of the type of explanation they return, also considering the different input data formats. The paper accounts for the most representative explainers to date, also discussing similarities and discrepancies of returned explanations through their visual appearance. A companion website to the paper is provided as a continuous update to new explainers as they appear. Moreover, a subset of the most robust and widely adopted explainers, are benchmarked with respect to a repertoire of quantitative metrics.

Source: Data mining and knowledge discovery (2023): 1719–1778. doi:10.1007/s10618-023-00933-9

Publisher: Kluwer Academic Publishers, Dordrecht ;, Stati Uniti d'America

Metrics