On the Complexity of SHAP-Score-Based Explanations: Tractability via Knowledge Compilation and Non-Approximability Results

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.

Model Interpretability through the Lens of Computational Complexity

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.

The Tractability of SHAP-Score-Based Explanations over Deterministic and Decomposable Boolean Circuits

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.