6 citations · 10 across the 6 of their papers we have counts for
5 papers · 1 filter
Prediction via Shapley Value Regression
Amr Alkhatib, Roman Bresson, Henrik Boström +1
Shapley values have several desirable, theoretically well-supported, properties for explaining black-box model predictions. Traditionally, Shapley values are computed post-hoc, lea…
Interpretable Graph Neural Networks for Heterogeneous Tabular Data
Amr Alkhatib, Henrik Boström
Many machine learning algorithms for tabular data produce black-box models, which prevent users from understanding the rationale behind the model predictions. In their unconstraine…
Explaining Predictions by Characteristic Rules
Amr Alkhatib, Henrik Boström, Michalis Vazirgiannis
Characteristic rules have been advocated for their ability to improve interpretability over discriminative rules within the area of rule learning. However, the former type of rule…
Approximating Score-based Explanation Techniques Using Conformal Regression
Amr Alkhatib, Henrik Boström, Sofiane Ennadir +1
Score-based explainable machine-learning techniques are often used to understand the logic behind black-box models. However, such explanation techniques are often computationally e…
Interpretable Graph Neural Networks for Tabular Data
Amr Alkhatib, Sofiane Ennadir, Henrik Boström +1
Data in tabular format is frequently occurring in real-world applications. Graph Neural Networks (GNNs) have recently been extended to effectively handle such data, allowing featur…