Publications

My research interests lie in how to quantify the role of graph topology in GNNs and to what extent we can improve the structural properties of the input graph to better exchange messages between layers.

• Graph Rewiring in GNNs to Mitigate Over-Squashing and Over-Smoothing : A Survey by Hugo Attali, Nathalie Pernelle, Davide Buscaldi, Fragkiskos D. Malliaros. Accepted at the International Joint Conference on Artificial Intelligence (IJCAI), Survey Track, 2026.

• Dynamic Triangulation-Based Graph Rewiring for Graph Neural Networks .  by Hugo Attali, Thomas Papastergiou, Nathalie Pernelle, Fragkiskos D. Malliaros. International Conference on Information and Knowledge Management (CIKM), 2025.

• Curvature Constrained MPPNS Improving Message passing with local Structural Properties.  by Hugo Attali, Davide Buscaldi, Nathalie Pernelle. International Journal Data and Knowledge Engineering (DKE), 2025.

• Tranductive Legal Judgment Prediction Combining BERT Embeddgins With Delaunay Based GNNs Transductive Legal Judgment Prediction Combining BERT Embeddings With Delaunay-Based GNNs  by Hugo Attali, Nadi Tomeh. Natural Legal Language Processing Worskshop (NLLP EMNLP 2024).

• Delaunay Graph: Addressing Over-Squashing and Over-Smoothing Using Delaunay Triangulation by Hugo Attali, Davide Buscaldi, Nathalie Pernelle. International Conference on Machine Learning (ICML), 2024.

• Matrice d’adjacence courbée : intégration de la courbure des arêtes dans la transmission des messages (nominated for best academic paper)  by Hugo Attali, Davide Buscaldi, Nathalie Pernelle. Conférence sur l’Extraction et la Gestion des Connaissances (EGC), 2024.

• Classification de documents par un réseau de neurones opérant sur les graphes dans l'espace hyperbolique by Adrien Guille, Hugo Attali. Conférence sur l’Extraction et la Gestion des Connaissances (EGC), 2023.

• Amélioration de l'architecture GAT par la prise en compte des arêtes du graphes by Hugo Attali, Adrien Guille, Stéphane Chrétien. Conférence sur l’Extraction et la Gestion des Connaissances (EGC), 2023.

• Document Classification with Hierarchical Graph Neural Networks by Adrien Guille, Hugo Attali. 18th International Workshop on Mining and Learning with Graphs (MLG @ ECML-PKDD), 2022.

• Classification interprétable de documents à l'aide d'un réseau de neurones opérant sur les graphes by Adrien Guille, Hugo Attali. Atelier Fouille de Textes (TextMine @ EGC), 2022.