Diffusion enabled Optimal Transport distances for graph matching
arXiv:2607.06646v1 Announce Type: new Abstract: This paper introduces Diffusion Semi-Relaxed Fused Gromov-Wasserstein (DsrFGW), a novel method for graph comparison that unifies node features and structural connectivity through optimal transport. While traditional Gromov-Wasserstein and semi-relaxed variants (srGW, srFGW) capture graph structure, they often struggle with sparse, noisy, or partially observed graphs. Inspired by Graph Diffusion Distance, which posits graphs are similar if they enab...
arXiv cs.LG
·Iman Seyedi, Francesco Archetti
·
// relacionados
Leia também
Blog
Rumo à desmistificação da criatividade dos modelos de difusão
Editorial
Leia de volta: como julgar uma imagem sem pedir opinião a ninguém
Blog
Plataforma AI-RAN da Nokia: um retorno ao rádio que roda em NVIDIA
Blog