Flowette: Flow Matching with Graphette Priors for Graph Generation

ArXi:2602.23566v2 Announce Type: replace-cross We study generative modeling of graphs with recurring subgraph motifs. We propose Flowette, a continuous flow matching framework that employs a graph neural network-based transformer to learn a velocity field over graph representations with node and edge attributes. Our model promotes topology-aware alignment through optimal transport-based coupling and encourages global structural coherence through regularisation. To incorporate domain-driven structural priors, we.