Watson, DS;
Gultchin, L;
Taly, A;
Floridi, L;
(2021)
Local Explanations via Necessity and Sufficiency: Unifying Theory and Practice.
In: de Campos, C and Maathuis, MH and Quaeghebeur, E, (eds.)
Proceedings of the 37th Conference on Uncertainty in Artificial Intelligence, UAI 2021.
(pp. pp. 1382-1392).
Association for Uncertainty in Artificial Intelligence (AUAI)
Preview |
Text
watson21a.pdf Download (617kB) | Preview |
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.
Type: | Proceedings paper |
---|---|
Title: | Local Explanations via Necessity and Sufficiency: Unifying Theory and Practice |
Event: | 37th Conference on Uncertainty in Artificial Intelligence (UAI 2021), 27-30 July 2021, Online |
Open access status: | An open access version is available from UCL Discovery |
Publisher version: | https://proceedings.mlr.press/v161/watson21a.html |
Language: | English |
Additional information: | This is the published version of record. For information on re-use, please refer to the publisher’s terms and conditions. |
UCL classification: | UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences > Dept of Statistical Science UCL > Provost and Vice Provost Offices > UCL BEAMS UCL |
URI: | https://discovery-pp.ucl.ac.uk/id/eprint/10144541 |
Archive Staff Only
View Item |