Pierre-Alexandre Murena

Welcome!

I am a junior professor in Human-Centric Machine Learning at the Technische Universität Hamburg (TUHH) and head of the Group on Human-Centric Machine Learning. I work on developping AI assistants which take into account the limitations, preferences and goals of the user.

Previously, I was postdoctoral researcher in the Multi-Source Probabilistic Inference group at the University of Helsinki (Finland) led by Assoc. Prof. Arto Klami, and a postdoctoral researcher in the PML group at Aalto University (Finland), working with Prof. Samuel Kaski. I was coordinating the team on Multi-Agent Modelling within the Finnish Center for Artificial Intelligence (FCAI).

I did my PhD in Télécom ParisTech in the DIG team (former DBWeb), under the supervision of Assoc. Prof. Jean-Louis Dessalles and Prof. Antoine Cornuéjols. I defended my PhD in December 2018, in front of a jury composed of Prof. Florence d'Alché-Buc (president), Prof. Amaury Habrard (reviewer), Prof. Shai Ben-David (reviewer), Prof. Gilles Richard (examiner), Assoc. Prof. Jean Lieber (examiner), Dr. Laurent Orseau (examiner). My work was rewarded by the second Best PhD award "Futur et Ruptures" of Institut Mines-Télécom (link, in French).

I am very involved in the research field of analogical reasoning. My main contribution is a novel approach based on Kolmogorov complexity. I am also interested in the theoretical question of the existence of continuous analogical proportions on manifolds, in particular manifolds of probability distributions. I am co-chair of the IJCAI-ECAI'22 Workshop on the Interactions between Analogical Reasoning and Machine Learning.

My papers and citations can be found on my Scholar or DBLP pages.

You can contact me by email: first.last [at] tuhh.de

Teaching activities

Aalto University - 2019-2020

Télécom ParisTech - 2017-2018

Télécom ParisTech - 2016-2017

Télécom ParisTech - 2015-2016

Publications

• Mustafa Mert Celikok, Pierre-Alexandre Murena, Samuel Kaski, Modeling needs user modeling, In Frontiers in Artificial Intelligence, 6, 2023

• Esteban Marquer, Safa Alsaidi, Amandine Decker, Pierre-Alexandre Murena, Miguel Couceiro, A Deep Learning Approach to Solving Morphological Analogies, In Case-Based Reasoning Research and Development: 30th International Conference, ICCBR 2022, Nancy, France, September 12–15, 2022, Proceedings (pp. 159-174).

• Pierre-Alexandre Murena, Measuring the Feasibility of Analogical Transfer using Complexity, In Proceedings of the Workshop on the Interactions between Analogical Reasoning and Machine Learning IARML@IJCAI-ECAI 2022.

• Pierre-Alexandre Murena and Marie Al-Ghossein, Inferring Case-Based Reasoners' Knowledge to Enhance Interactivity, In Case-Based Reasoning Research and Development: 29th International Conference, ICCBR 2021, Salamanca, Spain, September 13–16, 2021, Proceedings 29 (pp. 171-185).

• Safa Alsaidi, Amandine Decker, Puthineath Lay, Esteban Marquer, Pierre-Alexandre Murena, Miguel Couceiro, A Neural Approach for Detecting Morphological Analogies, In 2021 IEEE 8th International Conference on Data Science and Advanced Analytics (DSAA) (pp. 1-10).

• Safa Alsaidi, Amandine Decker, Puthineath Lay, Esteban Marquer, Miguel Couceiro and Pierre-Alexandre Murena, On the Transferability of Neural Models of Morphological Analogies, In Machine Learning and Principles and Practice of Knowledge Discovery in Databases: International Workshops of ECML PKDD 2021. [bibtex]

• Aurélien Nioche, Pierre-Alexandre Murena, Carlos de la Torre-Ortiz, Antti Oulasvirta, Improving Artificial Teachers by Considering how People Learn and Forget, In 26th International Conference on Intelligent User Interfaces (pp. 445-453). [bibtex] [code] [video] [page]

• Pierre-Alexandre Murena, Marie Al-Ghossein, Jean-Louis Dessalles, Antoine Cornuéjols, Solving Analogies on Words based on Minimal Complexity Transformation, in Proceedings of IJCAI-2020. [bibtex] [code] [short video] [long video]

• Antoine Cornuéjols, Pierre-Alexandre Murena, Raphaël Olivier, Transfer Learning by Learning Projections from Target to Source, accepted at Symposium on Intelligent Data Analysis 2020, Constanz, Germany, April 27-29, 2020. [bibtex]

• Marie Al-Ghossein, Pierre-Alexandre Murena, Talel Abdessalem, Anthony Barré and Antoine Cornuéjols , Adaptive Collaborative Topic Modeling for Online Recommendation, In Proceedings of the 12th ACM Conference on RecommenderSystems (pp. 338-346), Vancouver, Canada, October 2-7, 2018. [bibtex]

• Pierre-Alexandre Murena, Antoine Cornuéjols and Jean-Louis Dessalles, Opening the Parallelogram: Considerations on Non-Euclidean Analogies, in Proceedings of (ICCBR 2018) the 26th International Conference on Case-Based Reasoning, Stockholm, Sweden, July 9-12, 2018. [bibtex]

• Marie Al-Ghossein, Pierre-Alexandre Murena, Antoine Cornuéjols and Talel Abdessalem, Online Learning with Reoccurring Drifts: The Perspective of Case-Based Reasoning, in Proceedings of ICCBR 2018 Workshop on Synergies between CBR and Machine Learning, Stockholm, Sweden, July 12, 2018.

• Pierre-Alexandre Murena, Jérémie Sublime, Basarab Matei and Antoine Cornuéjols, An Information Theory based Approach to Multisource Clustering, in Proceedings of IJCAI-ECAI-2018 (Int. Joint Conf. on Artificial Intelligence), Stockholm, Sweden, July 13-19, 2018. [bibtex]

• Pierre-Alexandre Murena, Marie Al Ghossein, Talel Abdessalem and Antoine Cornuéjols, Adaptive Window Strategy for Topic Modeling in Document Stream, in Proceedings of IJCNN-2018 (Int. Joint Conf. on Neural Networks), Rio, Brasil, July 8-13, 2018. [bibtex]

• Pierre-Alexandre Murena, Jean-Louis Dessalles and Antoine Cornuéjols, A complexity based approach for solving Hofstadter's analogies, in Workshop on Computational Analogy, at ICCBR-2017 (Int. Conf. on Case-Based Reasoning), Trondheim, Norway, June 26-28, 2017. (longer version, not published)

• Pierre-Alexandre Murena, Antoine Cornuéjols and Jean-Louis Dessalles, Incremental Learning with the Minimum Description Length Principle, in Proceedings of IJCNN-2017 (Int. Joint Conf. on Neural Networks), Anchorage, USA, May 14-19, 2017.

• Jérémie Sublime, Basarab Matei and Pierre-Alexandre Murena, Analysis of the influence of diversity in collaborative and multi-view clustering, in Proceedings of IJCNN-2017 (Int. Joint Conf. on Neural Networks), Anchorage, USA, May 14-19, 2017.

• Pierre-Alexandre Murena and Antoine Cornuéjols, Minimum Description Length Principle applied to Structure Adaptation for Classification under Concept Drift, in Proceedings of IJCNN-2016 (Int. Joint Conf. on Neural Networks), Vancouver, Canada, July 25-29, 2016.