BibTex format
@inproceedings{Jiang:2022,
author = {Jiang, J and Rago, A and Toni, F},
title = {Should counterfactual explanations always be data instances?},
url = {http://hdl.handle.net/10044/1/98444},
year = {2022}
}
Citation
RIS format (EndNote, RefMan)
TY - CPAPER
AB - Counterfactual explanations (CEs) are an increasingly popular way of explaining machine learning classifiers. Predominantly, they amount to data instances pointing to potential changes to the inputs that would lead to alternative outputs. In this position paper we question the widespread assumption that CEs should always be data instances, and argue instead that in some cases they may be better understood in terms of special types of relations between input features and classification variables. We illustrate how a special type of these relations, amounting to critical influences, can characterise and guide the search for data instances deemed suitable as CEs. These relations also provide compact indications of which input features - rather than their specific values in data instances - have counterfactual value.
AU - Jiang,J
AU - Rago,A
AU - Toni,F
PY - 2022///
TI - Should counterfactual explanations always be data instances?
UR - http://hdl.handle.net/10044/1/98444
ER -
Contact us
Artificial Intelligence Network
South Kensington Campus
Imperial College London
SW7 2AZ
To reach the elected speaker of the network, Dr Rossella Arcucci, please contact:
To reach the network manager, Diana O'Malley - including to join the network - please contact: