1 citations · 2 across the 5 of their papers we have counts for
5 papers
Edge-Girth as a Structural Edge Feature for Graph Neural Networks
Lilian Marey, Charlotte Laclau
Graph neural networks (GNN) based on message passing are provably no more powerful than the one-dimensional Weisfeiler--Leman colour-refinement test (1-WL): two graphs it cannot te…
On the Realizability of Edge-Girth Sequences
Lilian Marey, Paul Hilaire, Charlotte Laclau
The edge-girth of an edge in a simple connected graph is the length of a shortest cycle containing , with if no such cycle exists, and the edge-girth sequence…
Structural Bias Beyond Homophily: A Study of Fairness in Link Prediction
Lilian Marey, Mathilde Perez, Tiphaine Viard +1
Graph link prediction (LP) plays a critical role in socially impactful applications such as job recommendation and friendship formation, making fairness a critical concern in this…
Modeling Musical Genre Trajectories through Pathlet Learning
Lilian Marey, Charlotte Laclau, Bruno Sguerra +2
The increasing availability of user data on music streaming platforms opens up new possibilities for analyzing music consumption. However, understanding the evolution of user prefe…
SimHawNet: A Modified Hawkes Process for Temporal Network Simulation
Mathilde Perez, Raphaël Romero, Bo Kang +3
Temporal networks allow representing connections between objects while incorporating the temporal dimension. While static network models can capture unchanging topological regulari…