Space Explanations of Neural Network Classification

TitleSpace Explanations of Neural Network Classification
Publication TypeConference Paper
Year of Publication2025
AuthorsLabbaf, Faezeh, Kolárik Tomáš, Blicha Martin, Fedyukovich Grigory, Wand Michael, and Sharygina Natasha
Conference Name37th CAV 2025
Abstract

We present a novel logic-based concept called Space Explanations for classifying neural networks that gives provable guarantees of the behavior of the network in continuous areas of the input feature space. To automatically generate space explanations, we leverage on a range of flexible Craig interpolation algorithms and unsatisfiable core generation.
Based on real-life case studies, ranging from small to medium to large size, we demonstrate that the generated explanations are more meaningful than those computed by the state-of-the-art