Metraipolis › archive › dc_c2720175f588
SLM-Conditioned Hierarchical Relation Routing for Labeled Property Graph Learning — arXiv:2608.26132
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.26132
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T15:20:45.960Z
- SHA-256 of the archived text
aa730ea2c22cabffe8a3dac44ae083aa6e8ebc6baf30c89a79d72518c4a4d4a3- Stable URL of this page
https://metraipolis.com/documento/dc_c2720175f588
How to cite
SLM-Conditioned Hierarchical Relation Routing for Labeled Property Graph Learning — arXiv:2608.26132 — arXiv (en), https://arxiv.org/abs/2608.26132 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c2720175f588 (Metraipolis archive dc_c2720175f588, sha256 aa730ea2c22cabffe8a3dac44ae083aa6e8ebc6baf30c89a79d72518c4a4d4a3)
BibTeX
@misc{dcc2720175f588,
title = {SLM-Conditioned Hierarchical Relation Routing for Labeled Property Graph Learning — arXiv:2608.26132},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.26132},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c2720175f588; sha256 aa730ea2c22cabffe8a3dac44ae083aa6e8ebc6baf30c89a79d72518c4a4d4a3},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.26132. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Labeled property graphs combine relational structure with heterogeneous textual and categorical properties attached to both nodes and relationships. Conventional graph neural networks typically represent these properties as static feature vectors, limiting their ability to determine which semantic evidence should influence message propagation for a particular prediction target. We propose SLM-Conditioned Hierarchical Relation Routing, an architecture that integrates a small language model directly into graph message selection. A topology GNN provides a stable structural representation and prediction anchor. For each target node, incident messages combine the neighbor's structural state, node-property encoding, relationship-property encoding, and relationship type. A parameter-efficient SLM processes structured graph soft tokens and produces a target-conditioned routing query. This query first selects relevant messages within each relationship type and subsequently routes information across relation-level summaries. The resulting representation provides a bounded residual update to the topology anchor, preserving structural evidence while allowing contextual semantic information to modify the prediction. The architecture supports interpretable analysis at both the neighbor and relationship-type levels and provides a general mechanism for integrating language-derived semantics into property-rich graph learning. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-28 in cs.CL). Categorie arXiv: Machine Learning (cs.LG) ; Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2608.26132 — 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 2026-10-17T15:15:18.106Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).