Amr Alkhatib

About Me

I am a PhD candidate at the EECS School of the KTH Royal Institute of Technology in Sweden, working under the supervision of Prof. Henrik Boström and Prof. Michalis Vazirgiannis.

My research focuses on Trustworthy Machine Learning, particularly in explainability, Conformal Prediction, and Graph Neural Networks. Additionally, I have hands-on experience with Natural Language Processing, Language Modeling, and Transformers.

News

[Jul. 2024] Our paper "Interpretable Graph Neural Networks for Tabular Data" is accepted to ECAI 2024.
[Jun. 2024] Presented our paper "Fast Approximation of Shapley Values with Limited Data" at 14th Scandinavian Conference on Artificial Intelligence.
[May 2024] Presented our paper "Interpretable Graph Neural Networks for Tabular Data" at ICLR 2024 DMLR Workshop.
[Nov. 2023] Our paper "UnboundAttack : Generating Unbounded Adversarial Attacks to Graph Neural Networks" is presented at 12th International Conference on Complex Networks.
[Sep. 2023] Presented our paper "Approximating Score-based Explanation Techniques Using Conformal Regression" at 12th Symposium on Conformal and Probabilistic Prediction with Applications.
[Sep. 2023] Our paper "Conformalized Adversarial Attack Detection for Graph Neural Networks" is presented at 12th Symposium on Conformal and Probabilistic Prediction with Applications.
[Sep. 2022] Presented our paper "Explaining Predictions by Characteristic Rules" at ECML PKDD 2022.
[Aug. 2022] Presented our paper "Assessing Explanation Quality by Venn Prediction" at 11th Symposium on Conformal and Probabilistic Prediction with Applications.

Publications

Interpretable Graph Neural Networks for Tabular Data

A. Alkhatib, S. Ennadir, H. Boström & M. Vazirgiannis.

The 27th European Conference on Artificial Intelligence (ECAI), 2024.

PDF Code
[Previous version] presented at the DMLR workshop in ICLR 2024.

Fast Approximation of Shapley Values with Limited Data

A. Alkhatib & H. Boström.

14th Scandinavian Conference on Artificial Intelligence (SCAI), 2024.

PDF Code
UnboundAttack : Generating Unbounded Adversarial Attacks to Graph Neural Networks

S. Ennadir, A. Alkhatib, G. Nikolentzos, M. Vazirgiannis & H. Boström.

12th International Conference on Complex Networks (CNA), 2023.

PDF Slides
Approximating Score-based Explanation Techniques Using Conformal Regression

A. Alkhatib, H. Boström, S. Ennadir & U. Johansson.

12th Symposium on Conformal and Probabilistic Prediction with Applications (COPA), 2023.

PDF Slides BibTex
Conformalized Adversarial Attack Detection for Graph Neural Networks

S. Ennadir, A. Alkhatib, H. Boström & M. Vazirgiannis.

12th Symposium on Conformal and Probabilistic Prediction with Applications (COPA), 2023.

PDF Slides BibTex
Explaining Predictions by Characteristic Rules

A. Alkhatib, H. Boström & M. Vazirgiannis.

The 19th European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases ECML PKDD, 2022.

PDF Code BibTex

Assessing Explanation Quality by Venn Prediction

A. Alkhatib, H. Boström & U. Johansson.

11th Symposium on Conformal and Probabilistic Prediction with Applications (COPA), 2022.

PDF BibTex
Emotional Tone Detection in Arabic Tweets

A. Alkhatib & S. R. El-Beltagy.

The 18th International Conference Computational Linguistics and Intelligent Text Processing (CICLing), 2017.

PDF Dataset BibTex

Prior Industrial Experience

[Nov 2017 - Jan 2021] AI Research Engineer at Mendel AI.
[Jan - Nov 2017] Data Scientist at IST Networks.
[Sep 2016 - Mar 2017] Research Assistant at the Nile University, Cairo.

Services

Conference Reviewer

Journal Reviewer

Machine Learning Journal

I would like to thank Sofiane Ennadir for allowing me to copy the format of his website. This website is powered by Jekyll and Minimal Light theme.