Local explanations via necessity and sufficiency: unifying theory and practice

David S. Watson, Limor Gultchin, Ankur Taly, Luciano Floridi
Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence, PMLR 161:1382-1392, 2021.

Abstract

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.

Cite this Paper


BibTeX
@InProceedings{pmlr-v161-watson21a, title = {Local explanations via necessity and sufficiency: unifying theory and practice}, author = {Watson, David S. and Gultchin, Limor and Taly, Ankur and Floridi, Luciano}, booktitle = {Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence}, pages = {1382--1392}, year = {2021}, editor = {de Campos, Cassio and Maathuis, Marloes H.}, volume = {161}, series = {Proceedings of Machine Learning Research}, month = {27--30 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v161/watson21a/watson21a.pdf}, url = {https://proceedings.mlr.press/v161/watson21a.html}, abstract = {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.} }
Endnote
%0 Conference Paper %T Local explanations via necessity and sufficiency: unifying theory and practice %A David S. Watson %A Limor Gultchin %A Ankur Taly %A Luciano Floridi %B Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2021 %E Cassio de Campos %E Marloes H. Maathuis %F pmlr-v161-watson21a %I PMLR %P 1382--1392 %U https://proceedings.mlr.press/v161/watson21a.html %V 161 %X 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.
APA
Watson, D.S., Gultchin, L., Taly, A. & Floridi, L.. (2021). Local explanations via necessity and sufficiency: unifying theory and practice. Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research 161:1382-1392 Available from https://proceedings.mlr.press/v161/watson21a.html.

Related Material