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.

Gianini, G., Lin, J., Mio, C., Damiani, E., Set-Based Counterfactuals in Partial Classification, in Communications in Computer and Information Science, (Inglese, 11-15 July 2022), Springer Science and Business Media Deutschland GmbH, Cham 2022:<<COMMUNICATIONS IN COMPUTER AND INFORMATION SCIENCE>>,1602 560-571. [10.1007/978-3-031-08974-9_45] [http://hdl.handle.net/10807/217005]

Set-Based Counterfactuals in Partial Classification

Lin, J.;
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.
Inglese
Communications in Computer and Information Science
19th International Conference on Information Processing and Management of Uncertainty in Knowledge-Based Systems, IPMU 2022
Inglese
11-lug-2022
15-lug-2022
978-3-031-08973-2
Springer Science and Business Media Deutschland GmbH
Gianini, G., Lin, J., Mio, C., Damiani, E., Set-Based Counterfactuals in Partial Classification, in Communications in Computer and Information Science, (Inglese, 11-15 July 2022), Springer Science and Business Media Deutschland GmbH, Cham 2022:<<COMMUNICATIONS IN COMPUTER AND INFORMATION SCIENCE>>,1602 560-571. [10.1007/978-3-031-08974-9_45] [http://hdl.handle.net/10807/217005]
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10807/217005
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact