Sylvie Coste-Marquis — accepted AI-conference papers

2026

Computing Coverage-Based Prime Implicant Explanations for Tree-Based Models

Gilles Audemard, Sylvie Coste-Marquis, Pierre Marquis, Mehdi Sabiri, Nicolas Szczepanski

IJCAI 2026

Coverage-based prime implicant explanations are formal explanations offering a number of valuable assets, especially in terms of faithfulness and generality. Unfortunately, deriving a coverage-based prime implicant explanation for an instance is computationally hard in the general case (the problem

Cited by 0 Scholar ↗

2021

On Belief Change for Multi-Label Classifier Encodings

Sylvie Coste-Marquis, Pierre Marquis

IJCAI 2021poster

An important issue in ML consists in developing approaches exploiting background knowledge T for improving the accuracy and the robustness of learned classifiers C. Delegating the classification task to a Boolean circuit Σ exhibiting the same input-output behaviour as C, the problem of exploiting T…

Cited by 12 Source ↗PDF ↗Scholar ↗