no code implementations • 6 Feb 2024 • O. Duranthon, L. Zdeborová
While graph convolutional networks show great practical promises, the theoretical understanding of their generalization properties as a function of the number of samples is still in its infancy compared to the more broadly studied case of supervised fully connected neural networks.
no code implementations • 6 Jun 2023 • O. Duranthon, L. Zdeborová
We show that there can be a considerable gap between the accuracy reached by this algorithm and the performance of the GNN architectures proposed in the literature.
no code implementations • 17 Mar 2023 • O. Duranthon, L. Zdeborová
The stochastic block model (SBM) is widely studied as a benchmark for graph clustering aka community detection.
no code implementations • 25 Sep 2019 • S. Goldt, M. Mézard, F. Krzakala, L. Zdeborová
Our analysis reveals two phenomena related to the dynamics of the networks and their ability to generalise that only appear when training on structured data sets.