Scalable Hierarchical Graph Generation via Soft Community Structure
Quick summary
arXiv:2610.12163v1 Announce Type: cross Abstract: Generating large attributed graphs requires reproducing the topology, generating attributes jointly with the structure, and remaining scalable. Many real-world graphs exist as a single large graph, so a generative model has to generalize from the one graph it is fit on, without independent samples. We present Schema, which recursively decomposes a reference graph into a hierarchy of soft communities, assigning each node a membership distribution. Generation is then split into three stages, each trained independently: (1) synthesizing node attri
Key takeaways
- arXiv:2610.12163v1 Announce Type: cross Abstract: Generating large attributed graphs requires reproducing the topology, generating attributes jointly with the structure, and remaining scalable.
- Many real-world graphs exist as a single large graph, so a generative model has to generalize from the one graph it is fit on, without independent samples.
- We present Schema, which recursively decomposes a reference graph into a hierarchy of soft communities, assigning each node a membership distribution.
Why it matters
“Scalable Hierarchical Graph Generation via Soft Community Structure” should be evaluated beyond branding and benchmark scores. Its practical importance will emerge in task accuracy, latency, unit cost, safety and integration with real workflows.
Member comments