Yassine Abbahaddou | Ecole Polytechnique

About Me

I am a Ph.D. Candidate at Ecole Polytechnique in Paris, conducting research at Laboratoire d'informatique de l'École polytechnique (LIX) under the supervision of of Professors Johannes F. Lutzeyer, Fragkiskos D. Malliaros, and Michalis Vazirgiannis . Proior to that, I completed a Master of Science in Applied mathematics and Engineering from Ecole Centrale Paris and a Master of Science in Mathematics, Machine Learning and Computer Vision from ENS Paris-Saclay ( M2 MVA Mathématiques, Vision, Apprentisage ).

My research interests span the broad area of Graph Neural Networks, Geometric Deep Learning and LLMs. I enjoy applying theoretical mathematical concepts to develop new machine learning algorithms for a variety of practical real-world applications.

My academic CV can be accessed here

Research Interests

Machine Learning: Representation Learning, Natural Language Processing.
Graph Neural Networks: Adversarial Robustness, Spectral Properties of Graph Shift Operator Matrices, Geometric GNNs.
Generative Models: Evaluating Coherent Generations, Multimodality, Diffusion models and LLMs.
Information Geometry: Asymptotic Theory of Statistical Inference, Invariant Geometry of Manifolds.

What's new?

[Dec 2024] New preprint on evaluating Time Series Generative Models.
[Nov. 2024] Three new preprints on Graph Machine Learning are now on Arxiv.
[May. 2024] I started a research internship at New York University (NYU).
[May. 2024] We presented our work on Robustness for GNNs at the DLCT Reading Group [Slides].
[Mar. 2024] We presented our ICLR paper at the Morocco AI Webinar [Slides | Recording].
[Jan. 2024] Our paper "Bounding the Expected Robustness of Graph Neural Networks Subject to Node Feature Attacks" is accepted to ICLR 2024.
[Dec. 2023] Our paper "Simple and Yet Fairly Effective Defense for Graph Neural Networks" is accepted to AAAI 2024.
[Oct. 2023] Our paper "Graph Neural Networks on Discriminative Graphs of Words" is accepted to the GLFrontiers Workshop at Neurips 2023.
[Jun. 2023] Our paper "Simple and Yet Fairly Effective Defense for Graph Neural Networks" is accepted to the AdvML workshop at ICML 2023.
[Sep. 2022] I started my PhD at Ecole Polytechnique.

Publications

ICLR

Bounding the Expected Robustness of Graph Neural Networks Subject to Node Feature Attacks

Yassine Abbahaddou,Sofiane Ennadir, Johannes Lutzeyer, Michalis Vazirgiannis & Henrik Boström

International Conference on Learning Representations (ICLR), 2024.

PDF Code BibTex
AAAI

Simple and Yet Fairly Effective Defense for Graph Neural Networks

Sofiane Ennadir, Yassine Abbahaddou,Johannes Lutzeyer, Michalis Vazirgiannis & Henrik Boström

Association for the Advancement of Artificial Intelligence (AAAI), 2023.

PDF Code BibTex

Preprint

Centrality Graph Shift Operators for Graph Neural Networks

Yassine Abbahaddou, Fragkiskos D. Malliaros, Johannes F. Lutzeyer, Michalis Vazirgiannis

Preprint.

PDF Code BibTex
Preprint

Gaussian Mixture Models Based Augmentation Enhances GNN Generalization

Yassine Abbahaddou, Fragkiskos D. Malliaros, Johannes F. Lutzeyer, Amine Mohamed Aboussalah, Michalis Vazirgiannis

Preprint.

PDF Code BibTex
Preprint

Grassmannian Geometry Meets Dynamic Mode Decomposition in DMD-GEN: A New Metric for Mode Collapse in Time Series Generative Models

Yassine Abbahaddou, Amine Mohamed Aboussalah

Preprint.

PDF Code BibTex
Preprint

Post-Hoc Robustness Enhancement in Graph Neural Networks with Conditional Random Fields

Yassine Abbahaddou, Sofiane Ennadir, Johannes F. Lutzeyer, Fragkiskos D. Malliaros, Michalis Vazirgiannis

Preprint.

PDF Code BibTex
Preprint

Atlas-Chat: Adapting Large Language Models for Low-Resource Moroccan Arabic Dialect

Guokan Shang, Hadi Abdine, Yousef Khoubrane, Amr Mohamed, Yassine Abbahaddou, Sofiane Ennadir, Imane Momayiz, Xuguang Ren, Eric Moulines, Preslav Nakov, Michalis Vazirgiannis, Eric Xing

Preprint.

PDF HuggingFace BibTex
GLFrontiers Workshop, Neurips

Graph Neural Networks on Discriminative Graphs of Words

Yassine Abbahaddou,Johannes Lutzeyer, Michalis Vazirgiannis

NeurIPS 2023 New Frontiers in Graph Learning Workshop (NeurIPS GLFrontiers), 2023.

PDF Code BibTex

Achievements & Awards

Top 1% students in Morocco (Concours National Commun ranking 2017) [Ranked 52-nd].
French Government’s Major-Excellence Scholarship (37,830 €) [Given to the top 40 Students].
Merit Scholarship of the CIUP (5,000 € ).
Resarch Grant from Institut Louis Bachelier (5,000 € ).
ICML Travel Grant (1,700 $ ).
NYU Visiting Research Scholarship.