no code implementations • 12 Jan 2024 • Pratik Karmakar, Mikaël Monet, Pierre Senellart, Stéphane Bressan
Shapley values, originating in game theory and increasingly prominent in explainable AI, have been proposed to assess the contribution of facts in query answering over databases, along with other similar power indices such as Banzhaf values.
no code implementations • 16 Apr 2021 • Marcelo Arenas, Pablo Barceló, Leopoldo Bertossi, Mikaël Monet
While in general computing Shapley values is an intractable problem, we prove a strong positive result stating that the $\mathsf{SHAP}$-score can be computed in polynomial time over deterministic and decomposable Boolean circuits.
no code implementations • NeurIPS 2020 • Pablo Barceló, Mikaël Monet, Jorge Pérez, Bernardo Subercaseaux
We prove that this notion provides a good theoretical counterpart to current beliefs on the interpretability of models; in particular, we show that under our definition and assuming standard complexity-theoretical assumptions (such as P$\neq$NP), both linear and tree-based models are strictly more interpretable than neural networks.
no code implementations • 28 Jul 2020 • Marcelo Arenas, Pablo Barceló Leopoldo Bertossi, Mikaël Monet
While in general computing Shapley values is a computationally intractable problem, it has recently been claimed that the SHAP-score can be computed in polynomial time over the class of decision trees.
