{
  "abstract": "Discrete diffusion models are a prominent family for graph generation, but standard class-conditional mechanisms embed the class signal in the denoiser during training, tying the conditioning mechanism to the trained model. Classifier guidance avoids this coupling in continuous domains by steering a frozen model with a classifier's gradient, but discrete graph diffusion samples discrete edge states, so gradients cannot propagate through the sampled graph. We introduce ProtoGuide, a post-hoc, backbone-agnostic framework that recovers an analogous mechanism. At each reverse step the denoiser's per-edge output is relaxed into a differentiable soft adjacency, embedded by a frozen Siamese graph neural network, and scored against a target-class prototype and its nearest competitor; the resulting per-edge gradient, damped by a cosine schedule, is injected back into the denoiser output. All components stay frozen, so guidance is retargeted by supplying a different prototype. On five classes of real-world networks and two architecturally different backbones, EDGE and DiGress, ProtoGuide raises macro classification accuracy from 50.7% to 73.5% and from 73.6% to 83.8%, and outperforms DiGress's built-in conditional training under our configuration. Gains are largest where the unguided models are weakest, and are not uniform across classes. Per-graph coverage remains high in most settings, while distributional effects are class-dependent. A Best-of-N selection baseline matches this accuracy given enough oversampling, but at a substantial cost in graph diversity. An independently initialized classifier, a directionality test, and a few-shot analysis support target-directed steering and robustness to very small support sets.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.15239",
  "author_total": 4,
  "authors": [
    {
      "name": "Salvatore Romano"
    },
    {
      "name": "Marco Grassia"
    },
    {
      "name": "Pietro Liò"
    },
    {
      "name": "Giuseppe Mangioni"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/f1tg2bmf3cxnt.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.15239",
  "fulltext_url": null,
  "id": "f1tg2bmf3cxnt",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.15239",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.AI"
    ],
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "physics.soc-ph"
    ],
    [
      "openalex",
      "1702|Advanced Graph Neural Networks"
    ]
  ],
  "openalex": "W7213364263",
  "pdf_url": "https://arxiv.org/pdf/2609.15239",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-14",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/f1tg2bmf3cxnt.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:21:25Z",
      "native_id": "2609.15239",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.15239"
    }
  ],
  "subjects": [
    {
      "field": "physics",
      "origin": "arxiv:physics.soc-ph",
      "subfield": "statistical-nonlinear"
    }
  ],
  "title": "ProtoGuide: Prototype-Driven Guidance for Class-Conditional Graph Generation",
  "title_text": "ProtoGuide: Prototype-Driven Guidance for Class-Conditional Graph Generation",
  "type": "preprint",
  "updated_at": "2026-10-30T12:21:25Z",
  "url": "https://research.draconitic.com/paper/f1tg2bmf3cxnt",
  "venue": "arXiv",
  "versions": []
}