Metraipolis › archive › dc_db5b7be72f77
Multi-Attractor GNNs: Set-Valued Expressivity Beyond Unique Equilibria — arXiv:2609.35274
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.35274
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T21:03:25.830Z
- SHA-256 of the archived text
c510e03063ec6f8db314f6007d63acc9d1ae8e44b361f5d4cae17721fdc85f39- Stable URL of this page
https://metraipolis.com/documento/dc_db5b7be72f77
How to cite
Multi-Attractor GNNs: Set-Valued Expressivity Beyond Unique Equilibria — arXiv:2609.35274 — arXiv (en), https://arxiv.org/abs/2609.35274 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_db5b7be72f77 (Metraipolis archive dc_db5b7be72f77, sha256 c510e03063ec6f8db314f6007d63acc9d1ae8e44b361f5d4cae17721fdc85f39)
BibTeX
@misc{dcdb5b7be72f77,
title = {Multi-Attractor GNNs: Set-Valued Expressivity Beyond Unique Equilibria — arXiv:2609.35274},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.35274},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_db5b7be72f77; sha256 c510e03063ec6f8db314f6007d63acc9d1ae8e44b361f5d4cae17721fdc85f39},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35274. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Recurrent and equilibrium graph neural networks (GNNs) often enforce a unique fixed point or use one training target per graph. Yet many combinatorial and scientific problems admit multiple valid solutions, with no preferred one. A designated target can then impose an arbitrary selection rule. For tasks invariant to node relabeling, a symmetric graph may have a symmetric solution set but no symmetric solution. We show that multiple equilibria enable one weight-tied message-passing GNN to represent set-valued equivariant maps: different initializations approach different valid solutions. Under stated regularity assumptions, we first construct globally Lipschitz, permutation-equivariant dynamics that converge almost surely to valid solutions and reach every solution branch with positive probability. We then establish approximate realization by recurrent message passing with continuous component maps, with arbitrarily small update and limiting errors and arbitrarily high probability. This goes beyond standard universality arguments: although message passing alone cannot distinguish symmetric nodes, the evolving state keeps nodes distinguishable at every finite step without auxiliary node identifiers. Such dynamics can be learned without solution labels using problem-specific energies. On Ising ground states, structural module detection in protein graphs, and chemical reaction steady states, the learned updates produce multiple high-quality predictions with high numerical convergence rates. They achieve better average solution quality than the tested unique-equilibrium, single-target, and feedforward baselines, while remaining competitive with much larger diffusion-based solvers. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.35274 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T20:29:03.311Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).