4 papers
Beyond Shapley: Efficient Computation of Asymmetric Shapley Values
Ezequiel Companeetz, Santiago Cifuentes, Sergio Abriola
We address the problem of explainability in machine learning models through feature attribution methods. In particular, we consider a variant of Shapley values known as Asymmetric…
Computational Complexity of Preferred Subset Repairs on Data-Graphs
Nina Pardal, Santiago Cifuentes, Edwin Pin +2
Preferences are a pivotal component in practical reasoning, especially in tasks that involve decision-making over different options or courses of action that could be pursued. In t…
The Distributional Uncertainty of the SHAP score in Explainable Machine Learning
Santiago Cifuentes, Leopoldo Bertossi, Nina Pardal +3
Attribution scores reflect how important the feature values in an input entity are for the output of a machine learning model. One of the most popular attribution scores is the SHA…
Measuring well quasi-ordered finitary powersets
Sergio Abriola, Simon Halfon, Aliaume Lopez +3
The complexity of a well-quasi-order (wqo) can be measured through three ordinal invariants: the width as a measure of antichains, height as a measure of chains, and maximal order…