Showing cs.LGShow all
3 papers · 1 filter
cs.LG2025
Chaining 2-FWL GNNs for Combinatorial Graph Alignment
Marc Lelarge
For the combinatorial graph alignment problem (GAP) -- finding the node correspondence that maximizes the number of common edges (nce) between two unlabeled graphs -- properly init…
cs.LG2025
Graph Alignment for Benchmarking Graph Neural Networks and Learning Positional Encodings
Adrien Lagesse, Marc Lelarge
We propose a novel benchmarking methodology for graph neural networks (GNNs) based on the graph alignment problem, a combinatorial optimization task that generalizes graph isomorph…
cs.LG2023
Automatic Rao-Blackwellization for Sequential Monte Carlo with Belief Propagation
Waïss Azizian, Guillaume Baudart, Marc Lelarge
Exact Bayesian inference on state-space models~(SSM) is in general untractable, and unfortunately, basic Sequential Monte Carlo~(SMC) methods do not yield correct approximations fo…