83 citations · 332 across the 27 of their papers we have counts for
33 papers
A Generalized Tikhonov Layer for Interpretable-by-design Graph Neural Networks
Nicolas Tremblay, Benjamin Ricaud, Filippo Maria Bianchi
We propose the Tikhonov layer, a graph neural network layer that is interpretable by design: once trained, its learned parameters directly reveal which node features and which aspe…
Convergence of Message Passing Graph Neural Networks with Generic Aggregation On Large Random Graphs
Matthieu Cordonnier, Nicolas Keriven, Nicolas Tremblay +1
We study the convergence of message passing graph neural networks on random graph models to their continuous counterpart as the number of nodes tends to infinity. Until now, this c…
A Faster Sampler for Discrete Determinantal Point Processes
Simon Barthelmé, Nicolas Tremblay, Pierre-Olivier Amblard
Discrete Determinantal Point Processes (DPPs) have a wide array of potential applications for subsampling datasets. They are however held back in some cases by the high cost of sam…
Smoothing complex-valued signals on Graphs with Monte-Carlo
Hugo Jaquard, Michaël Fanuel, Pierre-Olivier Amblard +3
We introduce new smoothing estimators for complex signals on graphs, based on a recently studied Determinantal Point Process (DPP). These estimators are built from subsets of edges…
Variance Reduction for Inverse Trace Estimation via Random Spanning Forests
Yusuf Yigit Pilavci, Pierre-Olivier Amblard, Simon Barthelme +1
The trace $\tr(q(\ma{L} + q\ma{I})^{-1})$, where $\ma{L}$ is a symmetric diagonally dominant matrix, is the quantity of interest in some machine learning problems. However, its dir…
Gaussian Process Regression in the Flat Limit
Simon Barthelmé, Pierre-Olivier Amblard, Nicolas Tremblay +1
Gaussian process (GP) regression is a fundamental tool in Bayesian statistics. It is also known as kriging and is the Bayesian counterpart to the frequentist kernel ridge regressio…