Metraipolis › archive › dc_68d1007ed61e
Beyond Static Graph World Models: Learning Stochastic Latent Dynamics over Evolving Topologies — arXiv:2609.28670
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.28670
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T04:27:04.905Z
- SHA-256 of the archived text
e3bee0c522f31e2cf24580d30719662cfc25ecce1f1d121498181d3778999e56- Stable URL of this page
https://metraipolis.com/documento/dc_68d1007ed61e
How to cite
Beyond Static Graph World Models: Learning Stochastic Latent Dynamics over Evolving Topologies — arXiv:2609.28670 — arXiv (en), https://arxiv.org/abs/2609.28670 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_68d1007ed61e (Metraipolis archive dc_68d1007ed61e, sha256 e3bee0c522f31e2cf24580d30719662cfc25ecce1f1d121498181d3778999e56)
BibTeX
@misc{dc68d1007ed61e,
title = {Beyond Static Graph World Models: Learning Stochastic Latent Dynamics over Evolving Topologies — arXiv:2609.28670},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.28670},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_68d1007ed61e; sha256 e3bee0c522f31e2cf24580d30719662cfc25ecce1f1d121498181d3778999e56},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.28670. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Graph-based world models have recently emerged as a means of learning transitions over relational state representations. However, existing approaches are largely limited to fixed-topology graphs or deterministic, fully observable environments. We propose the Graph Dynamics Model (GDM), a world model for graph-structured observations that is designed to handle the more general setting of evolving topologies in stochastic and partially observable environments. The GDM uses a sparse recurrent adjacency matrix to model topology updates and perform message passing, together with a recurrent state-space architecture for modelling stochastic transitions. Furthermore, we identify a gap in the evaluation of graph-based world models, as existing methods do not provide a means of comparing predicted and true distributions over the joint graph state comprising the interdependent topology, node features, and graph features. We therefore introduce the Graph Distribution Distance (GDD) metric, which uses maximum mean discrepancy with a graph kernel to comprehensively compare joint next-state distributions. We evaluate the GDM across several environments, including stochastic and partially observable settings. We demonstrate that GDM outperforms baseline models and displays zero-shot generalisation on large graphs. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-25 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Social and Information Networks (cs.SI). Pagina del lavoro: https://arxiv.org/abs/2609.28670 — 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 2026-10-08T03:50:57.944Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).