11 citations · 40 across the 10 of their papers we have counts for
Showing 2023Show all
2 papers · 1 filter
cs.LG2023★ 4 cited
Graph Neural Networks Go Forward-Forward
Daniele Paliotta, Mathieu Alain, Bálint Máté +1
We present the Graph Forward-Forward (GFF) algorithm, an extension of the Forward-Forward procedure to graphs, able to handle features distributed over a graph's nodes. This allows…
stat.ML2023★ 5 cited
Learning Interpolations between Boltzmann Densities
Bálint Máté, François Fleuret
We introduce a training objective for continuous normalizing flows that can be used in the absence of samples but in the presence of an energy function. Our method relies on either…