Citation

BibTex format

@inproceedings{Leofante:2023:kr.2023/78,
author = {Leofante, F and Botoeva, E and Rajani, V},
doi = {kr.2023/78},
pages = {763--768},
publisher = {IJCAI Organization},
title = {Counterfactual explanations and model multiplicity: a relational verification view},
url = {http://dx.doi.org/10.24963/kr.2023/78},
year = {2023}
}

RIS format (EndNote, RefMan)

TY  - CPAPER
AB - We study the interplay between counterfactual explanationsand model multiplicity in the context of neural network clas-sifiers. We show that current explanation methods often pro-duce counterfactuals whose validity is not preserved undermodel multiplicity. We then study the problem of generatingcounterfactuals that are guaranteed to be robust to model multiplicity, characterise its complexity and propose an approach to solve this problem using ideas from relational verification.
AU - Leofante,F
AU - Botoeva,E
AU - Rajani,V
DO - kr.2023/78
EP - 768
PB - IJCAI Organization
PY - 2023///
SN - 2334-1033
SP - 763
TI - Counterfactual explanations and model multiplicity: a relational verification view
UR - http://dx.doi.org/10.24963/kr.2023/78
UR - http://hdl.handle.net/10044/1/104738
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:

ai-speaker@imperial.ac.uk

To reach the network manager, Diana O'Malley - including to join the network - please contact:

ai-net-manager@imperial.ac.uk