ProToMEx: Rapid, Interpretable Explanations via Structured Representations
It is demonstrated empirically that ProToMEx not only produces explanations of comparable fidelity to popular methods like SHAP and LIME but also drastically reduces the amortised computational cost of generating local explanations, making it highly suitable for real-time applications.
A. Georgara, Adarsh Valoor, Sarvapali D. Ramchurn
· 0 citations