Graphs are invariant under node permutations, motivating permutation-equivariant architectures in generative models. In flow matching, however, symmetry also affects the source-target coupling: one must choose both which graphs to pair and which node representatives to align. We study these two forms of alignment, term...
The key ingredient is that, for a constructed jump bridge, a parametrization of the jump kernel densities by scaled Gaussians admits closed-form expressions for the Kullback-Leibler divergence, allowing simulation-free training.
O. Pfohl, J. Chemseddine, P. Hagemann et al.· 1 citation
This work develops this perspective theoretically, showing that quotient couplings can be lifted to aligned representatives without additional cost and that symmetrization yields equivariant flow-matching minimizers, including for categorical endpoint prediction.
Moritz Piening, C. Wald· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.