Given a class label y assigned by a classifier to a point x in feature space, the counterfactual generation task, in its simplest form, consists of finding the minimal edit that moves the feature vector to a new point x′, which the classifier maps to a pre-specified target class y′ = y. Counterfactuals provide a local explanation to a classifier model, by answering the questions “Why did the model choose y instead of y′: what changes to x would make the difference?”. An important aspect in classification is ambiguity: typically, the description of an instance is compatible with more than one class. When ambiguity is too high, a suitably designed classifier can map an instance x to a class set Y of alternatives, rather than to a single class, so as to reduce the likelihood of wrong decisions. In this context, known as set-based classification, one can discuss set-based counterfactuals. In this work, we extend the counterfactual generation problem – normally expressed as a constrained optimization problem – to set-based counterfactuals. Using non-singleton counterfactuals, rather than singletons, makes the problem richer under several aspects, related to the fact that non-singleton sets allow for a wider spectrum of relationships among them: (1) the specification of the target set-based class Y ′ is more varied (2) the target solution x′ that ought to be mapped to Y ′ is not granted to exist, and, in that case, (3) since one might end up with the availability of a number of feasible alternatives to Y ′, one has to include the degree of partial fulfillment of the solution into the loss function of the optimization problem.
Set-Based Counterfactuals in Partial Classification / G. Gianini, J. Lin, C. Mio, E. Damiani (COMMUNICATIONS IN COMPUTER AND INFORMATION SCIENCE). - In: Information Processing and Management of Uncertainty in Knowledge-Based Systems / [a cura di] D. Ciucci, I. Couso, J. Medina, D. Ślęzak, D. Petturiti, B. Bouchon-Meunier, R.R. Yager. - [s.l] : Springer, 2022. - ISBN 978-3-031-08973-2. - pp. 560-571 (( convegno Information Processing and Management of Uncertainty in Knowledge-Based Systems. IPMU 202 tenutosi a Milano nel 2022 [10.1007/978-3-031-08974-9_45].
Set-Based Counterfactuals in Partial Classification
G. Gianini
Primo
;J. LinSecondo
;C. MioPenultimo
;E. DamianiUltimo
2022
Abstract
Given a class label y assigned by a classifier to a point x in feature space, the counterfactual generation task, in its simplest form, consists of finding the minimal edit that moves the feature vector to a new point x′, which the classifier maps to a pre-specified target class y′ = y. Counterfactuals provide a local explanation to a classifier model, by answering the questions “Why did the model choose y instead of y′: what changes to x would make the difference?”. An important aspect in classification is ambiguity: typically, the description of an instance is compatible with more than one class. When ambiguity is too high, a suitably designed classifier can map an instance x to a class set Y of alternatives, rather than to a single class, so as to reduce the likelihood of wrong decisions. In this context, known as set-based classification, one can discuss set-based counterfactuals. In this work, we extend the counterfactual generation problem – normally expressed as a constrained optimization problem – to set-based counterfactuals. Using non-singleton counterfactuals, rather than singletons, makes the problem richer under several aspects, related to the fact that non-singleton sets allow for a wider spectrum of relationships among them: (1) the specification of the target set-based class Y ′ is more varied (2) the target solution x′ that ought to be mapped to Y ′ is not granted to exist, and, in that case, (3) since one might end up with the availability of a number of feasible alternatives to Y ′, one has to include the degree of partial fulfillment of the solution into the loss function of the optimization problem.File | Dimensione | Formato | |
---|---|---|---|
samplepaper_revised.pdf
accesso riservato
Tipologia:
Post-print, accepted manuscript ecc. (versione accettata dall'editore)
Dimensione
126.91 kB
Formato
Adobe PDF
|
126.91 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
978-3-031-08974-9_45.pdf
accesso riservato
Tipologia:
Publisher's version/PDF
Dimensione
246.9 kB
Formato
Adobe PDF
|
246.9 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.