Amr Alkhatib

According to our database, Amr Alkhatib authored at least 8 papers between 2022 and 2024.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2024

Interpretable Graph Neural Networks for Heterogeneous Tabular Data.

Amr Alkhatib, Henrik Boström

CoRR, 2024

Fast Approximation of Shapley Values with Limited Data.

Amr Alkhatib, Henrik Boström

Proceedings of the 14th Scandinavian Conference on Artificial Intelligence SCAI 2024, 2024

Interpretable Graph Neural Networks for Tabular Data.

Amr Alkhatib, Sofiane Ennadir, Henrik Boström, Michalis Vazirgiannis

Proceedings of the ECAI 2024 - 27th European Conference on Artificial Intelligence, 19-24 October 2024, Santiago de Compostela, Spain, 2024

2023

Conformalized Adversarial Attack Detection for Graph Neural Networks.

Sofiane Ennadir, Amr Alkhatib, Henrik Boström, Michalis Vazirgiannis

Proceedings of the Conformal and Probabilistic Prediction with Applications, 2023

Approximating Score-based Explanation Techniques Using Conformal Regression.

Amr Alkhatib, Henrik Boström, Sofiane Ennadir, Ulf Johansson

Proceedings of the Conformal and Probabilistic Prediction with Applications, 2023

UnboundAttack: Generating Unbounded Adversarial Attacks to Graph Neural Networks.

Sofiane Ennadir, Amr Alkhatib, Giannis Nikolentzos, Michalis Vazirgiannis, Henrik Boström

Proceedings of the Complex Networks & Their Applications XII, 2023

2022

Explaining Predictions by Characteristic Rules.

Amr Alkhatib, Henrik Boström, Michalis Vazirgiannis

Proceedings of the Machine Learning and Knowledge Discovery in Databases, 2022

Assessing Explanation Quality by Venn Prediction.

Amr Alkhatib, Henrik Boström, Ulf Johansson

Proceedings of the Conformal and Probabilistic Prediction with Applications, 2022