Ahcène Boubekki

Postdoctoral Researcher

about me

I am a postdoctoral researcher at the Machine Learning and Uncertainty group at Physikalisch-Technische Bundesanstalt (Berlin).

Prior to joining the PTB, I was a postdoctoral researcher at the Machine Learning group at University in Tromsø (Norway).

I did my PhD at the Machine Learning Group under te supervision of Ulf Brefeld at the Leuphana University of Lüneburg.

I received a Master and a Bachelor in pure Mathematics from the University Pierre et Marie Curie, Paris 6, now aka Sorbonne Université🤷.

research interests

I am interested in explainable ai, unsupervised learning, representation learning, generative models, probabilistic models, user modeling and understanding, education data mining.

publications

  • S. Haufe, R. Wilming, B. Clark, R. Zhumagambetov, D. Panknin, A. Boubekki. Explainable AI needs formal notions of explanation correctness. Intepretable AI Workshop @ NeurIPS (2024) [link]
  • A. Boubekki, S. Fadel, S.Mair. Leveraging Activations for Superpixel Explanations. ArXiv [link]
  • S. Gautam, A. Boubekki, M. Höhne, M. Kampffmeyer . Prototypical Self-Explainable Models Without Re-training. Transactions on Machine Learning Research (2024). [link]
  • R. Clark et al. EXACT: Towards a platform for empirically benchmarking Machine Learning model explanation methods (2024). [link]
  • R. Kjærsgaard, A. Boubekki, L.H. Clemmensen. Pantypes: Diverse Representatives for Self-Explainable Models. AAAI Conference on Artificial Intelligence (2024). [link]
  • K.V. Olesen, A. Boubekki, M.C. Kampffmeyer, R. Jenssen, A.N. Christensen, S. Hørlück, L.H. Clemmensen. A Contextually Supported Abnormality Detector for Maritime Trajectories. Journal of Marine Science and Engineering (2023). [link]
  • K.K. Wickstrøm, D.J. Trosten, S. Løkse, A. Boubekki, K.Ø. Mikalsen, M. Kampffmeyer, R. Jenssen. RELAX: Representation Learning Explainability. International Journal of Computer Vision, 1-27, 2023.[link]
  • D. Singh, A. Boubekki, R. Jenssen, M. Kampffmeyer. SuperCM: Revisiting Clustering for Semi-Supervised Learning. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023. [link]
  • A. Blázquez-García, K.K. Wickstrøm, S. Yu, K.Ø. Mikalsen, A. Boubekki, A. Conde, U. Mori, R. Jenssen, J. A. Lozano. Selective Imputation for Multivariate Time Series Datasets with Missingc Values. IEEE Transactions on Knowledge and Data Engineering, 2023. [link]
  • S. Gautam, A. Boubekki, S. Hansen, S. A. Salahuddin, R. Jenssen, M. Höhne, M. Kampffmeyer. ProtoVAE: A Trustworthy Self-Explainable Prototypical Variational Model. Advances in Neural Information Processing Systems, 2022. [link]
  • A. Boubekki, M. Kampffmeyer, U. Brefeld, R. Jenssen. Joint optimization of an autoencoder for clustering and embedding. Machine Learning, 2021. [link]
  • A. Boubekki, J. Nordhaug Myhre, L. T. Luppino, K. O. Mikalsen, A. Revhaug, R. Jenssen. Clinically relevant features for predicting the severity of surgical site infections. IEEE Journal of Biomedical and Health Informatics, 2021. [link]
  • I. Pandarova, T. Schmidt, J. Hartig, A. Boubekki, R. D. Jones, U. Brefeld, Predicting the difficulty of exercise items for dynamic difficulty adaptation in adaptive language tutoring. International Journal of Artificial Intelligence in Education, 2019. [link]
  • A. Boubekki, S. Jain, and U. Brefeld. Mining User Trajectories in Electronic Text Books. Proceedings of Educational Data Mining, 2018. [link]
  • J. Reubold, A. Boubekki, T. Strufe, and U. Brefeld. Infinite Mixtures of Markov Chains. New Frontiers in Mining Complex Patterns, LNAI 10785, Springer, 2018. [link]
  • J. Reubold, A. Boubekki, T. Strufe, and U. Brefeld. Bayesian User Behavior Models. Proceedings of the ECML/PKDD Workshop on New Frontiers in Mining Complex Patterns, 2017. [link]
  • S. Mair, A. Boubekki, and U. Brefeld. Frame-based Data Factorizations. Proceedings of the International Conference on Machine Learning, 2017. [link]
  • S. Mair, A. Boubekki, and U. Brefeld. Frame-based Matrix Factorizations (abstract). Proceedings of the LWDA Workshop on Knowledge Discovery, Data Mining and Machine Learning (KDML), 2017.
  • A. Boubekki, C. L. Lucchesi, U. Brefeld, and W. Stille. Propagating Maximum Capacities for Recommendation. Proceedings of the German Conference on Artificial Intelligence, 2017. [link]
  • A. Boubekki, U. Kröhne, F. Goldhammer, W. Schreiber, and U. Brefeld. In S. Michaelis, N. Piatkowski, and M. Stolpe (Eds.): Data-Driven Analyses of Electronic Text Books. Solving Large Scale Learning Tasks. Challenges and Algorithms -- Essays Dedicated to Katharina Morik on the Occasion of Her 60th Birthday. Lecture Notes in Artificial Intelligence 9580, Springer, 362-376, 2016.
  • Delacroix T., Boubekki A., Lenca P. and Lallich S., Constrained Independence for Detecting Interesting Patterns, Proceedings of the International Conference on Data Science and Advanced Analytics (DSAA), 2015. [link]
  • Boubekki A., Kröhne U., Goldhammer F., Schreiber W., Brefeld U., Toward Data-Driven Analyses of Electronic Text Books, Proceedings of the International Conference on Educational Data Mining, 2015. [link]
  • Boubekki A., Brefeld U. and Delacroix T., Generalising IRT to Discriminate Between Examinees, Proceedings of the International Conference on Educational Data Mining, 2015.
  • Boubekki A., Bengs D., Mining Implications From Data, Proceedings of the LWA 2014 Workshops: KDML, IR, FGWM, Aachen, Germany, September 8-10, 2014.
  • Delacroix T., Boubekki A., An application of multiple behavior SIA for analyzing data from student exams, in The SIA Approach for Semantic and non-Symmetric Data Analysis, Régnier, Almouloud & Gras (Eds), Educaçao Matematica Pesquisa, Sao Paulo, v.16, n.3, pp.773-794, 2014. [link]