no code implementations • 27 Mar 2023 • Luisa Werner, Nabil Layaïda, Pierre Genevès, Sarah Chlyah
On one hand, neural methods, such as graph neural networks, have proven to be robust tools for learning rich representations of noisy graphs.
no code implementations • 27 Feb 2021 • Raouf Kerkouche, Gergely Ács, Claude Castelluccia, Pierre Genevès
This bandwidth and corresponding processing costs could be prohibitive if the participating entities are, for example, mobile devices.
no code implementations • 10 Nov 2020 • Raouf Kerkouche, Gergely Ács, Claude Castelluccia, Pierre Genevès
In this paper, compressive sensing is used to reduce the model size and hence increase model quality without sacrificing privacy.