8 papers
CoRe-GNN: Multilevel Message passing on Coarsened graphs
Antonin Joly, Nicolas Keriven, Aline Roumy
Training Graph Neural Networks on large graphs is challenged by the memory cost of storing all node representations across layers. We show that several existing scalable approaches…
Discovering shared interpretable operations in image compression autoencoders
Caroline Mazini Rodrigues, Nicolas Keriven, Thomas Maugey
With the increasing adoption of deep learning for applications such as image compression, improvements in the rate-distortion trade-off have been achieved at the cost of increasing…
Efficient training for compact compression models via sequential distillation
Caroline Mazini Rodrigues, Nicolas Keriven, Thomas Maugey
Deep learning models for image compression often face practical limitations in hardware-constrained applications. Although these models achieve high-quality reconstructions, they a…
Backward Oversmoothing: why is it hard to train deep Graph Neural Networks?
Nicolas Keriven
Oversmoothing has long been identified as a major limitation of Graph Neural Networks (GNNs): input node features are smoothed at each layer and converge to a non-informative repre…
Statistical Consistency of Discrete-to-Continuous Limits of Determinantal Point Processes
Hugo Jaquard, Nicolas Keriven
We investigate the limiting behavior of discrete determinantal point processes (DPPs) towards continuous DPPs when the size of the set to sample from goes to infinity. We propose a…
Taxonomy of reduction matrices for Graph Coarsening
Antonin Joly, Nicolas Keriven, Aline Roumy
Graph coarsening aims to diminish the size of a graph to lighten its memory footprint, and has numerous applications in graph signal processing and machine learning. It is usually…