Citation

BibTex format

@article{Rago:2023,
author = {Rago, A and Russo, F and Albini, E and Toni, F and Baroni, P},
journal = {Journal of Applied Logics},
pages = {421--449},
title = {Explaining classifiers’ outputs with causal models and argumentation},
url = {https://briziorusso.github.io/files/pdf/research/explain_ifcolog.pdf},
volume = {10},
year = {2023}
}

RIS format (EndNote, RefMan)

TY  - JOUR
AB - We introduce a conceptualisation for generating argumentation frameworks (AFs) from causal models for the purpose of forging explanations for mod-els’ outputs. The conceptualisation is based on reinterpreting properties of semantics of AFs as explanation moulds, which are means for characterising argumentative relations. We demonstrate our methodology by reinterpreting the property of bi-variate reinforcement in bipolar AFs, showing how the ex-tracted bipolar AFs may be used as relation-based explanations for the outputs of causal models. We then evaluate our method empirically when the causal models represent (Bayesian and neural network) machine learning models for classification. The results show advantages over a popular approach from the literature, both in highlighting specific relationships between feature and classification variables and in generating counterfactual explanations with respect to a commonly used metric.
AU - Rago,A
AU - Russo,F
AU - Albini,E
AU - Toni,F
AU - Baroni,P
EP - 449
PY - 2023///
SN - 2631-9810
SP - 421
TI - Explaining classifiers’ outputs with causal models and argumentation
T2 - Journal of Applied Logics
UR - https://briziorusso.github.io/files/pdf/research/explain_ifcolog.pdf
UR - http://hdl.handle.net/10044/1/105085
VL - 10
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