Explaining robust additive utility models by sequences of preference swaps

Belahcene, Khaled; Labreuche, Christophe; Maudet, Nicolas; Mousseau, Vincent; Ouerdane, Wassila

doi:10.1007/s11238-016-9560-1

Cited by 9 publications

(3 citation statements)

References 27 publications

(28 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, the overall method is clearly polynomial, with a linear pre-treatment over the sum of k i 's, followed by a sorting algorithm, after which Algorithm 1 is linear over the number of attributes. 4 As log p…”

Section: Generic Casementioning

confidence: 99%

“…However, explainable AI tools have been mostly if not exclusively applied to precise models, at least in the machine learning domain (this is less true, e.g., in preference modelling [4]). Yet, in some applications involving sensitive issues or where the decision maker wants to identify ambiguous cases, it may be preferable to use models that will return sets of classes in some cases where information is missing rather than always returning a point-valued prediction.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Explaining Robust Classification Through Prime Implicants

Willot

Destercke

Belahcene

2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

In this paper, we investigate how robust classification results can be explained by the notion of prime implicants, focusing on explaining pairwise dominance relations. By robust, we mean that we consider imprecise models that may abstain to classify or to compare two classes when information is insufficient. This will be reflected by considering (convex) sets of probabilities. By prime implicants, we understand a minimal number of attributes whose value needs to be known before stating that one class dominates/is preferred to another.

show abstract

Section: Generic Casementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Explaining Robust Classification Through Prime Implicants

Willot

Destercke

Belahcene

2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…al. [27] who -in the context of decision-aiding -aim to build incremental explanations using preference relations. In our case, this would correspond to preferring simple constraints to more complex combinations of constraints through a cost function.…”

Section: Related Workmentioning

confidence: 99%

A framework for step-wise explaining how to solve constraint satisfaction problems

Bogaerts,

Gamba,

Guns

2020

Preprint

View full text Add to dashboard Cite

We explore the problem of step-wise explaining how to solve constraint satisfaction problems, with a use case on logic grid puzzles. More specifically, we study the problem of explaining the inference steps that one can take during propagation, in a way that is easy to interpret for a person. Thereby, we aim to give the constraint solver explainable agency, which can help in building trust in the solver by being able to understand and even learn from the explanations. The main challenge is that of finding a sequence of simple explanations, where each explanation should aim to be as cognitively easy as possible for a human to verify and understand. This contrasts with the arbitrary combination of facts and constraints that the solver may use when propagating. We propose the use of a cost function to quantify how simple an individual explanation of an inference step is, and identify the explanation-production problem of finding the best sequence of explanations of a CSP. Our approach is agnostic of the underlying constraint propagation mechanisms, and can provide explanations even for inference steps resulting from combinations of constraints. In case multiple constraints are involved, we also develop a mechanism that allows to break the most difficult steps up and thus gives the user the ability to zoom in on specific parts of the explanation. Our proposed algorithm iteratively constructs the explanation sequence by using an optimistic estimate of the cost function to guide the search for the best explanation at each step. Our experiments on logic grid puzzles show the feasibility of the approach in terms of the quality of the individual explanations and the resulting explanation sequences obtained.

show abstract

Robust Ordinal Regression for Multiple Criteria Decision Aiding

Kadziński

2022

Intelligent Decision Support Systems

View full text Add to dashboard Cite

Explaining robust additive utility models by sequences of preference swaps

Cited by 9 publications

References 27 publications

Explaining Robust Classification Through Prime Implicants

Explaining Robust Classification Through Prime Implicants

A framework for step-wise explaining how to solve constraint satisfaction problems

Robust Ordinal Regression for Multiple Criteria Decision Aiding

Contact Info

Product

Resources

About