EUVIMEDEUVIMED entdecken
Crossref

VF-GraphSAGE: Vertex feature-enhanced graph neural network for room classification in residential floor plans

S. Hadi Ghoddusifar

International Journal of Architectural Computing · 10.11.2026

DOI: 10.1177/14780771261500170 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Architectural Computing, online erschienen am 10.11.2026. Verfasst von S. Hadi Ghoddusifar. Die Arbeit nennt 24 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Graph-based floor plan understanding has advanced rapidly through generative models, yet the analytical task of room-type classification — a prerequisite for layout validation and a quality signal for downstream synthesis — has received far less attention. This paper introduces VF-GraphSAGE, a graph neural network that fuses explicit room-boundary geometry with inductive graph learning. Each room is a node in a plan-level access graph described by two streams: a compact geometric descriptor and a fixed-length encoding of its raw polygon vertices, combined with GraphSAGE message passing over door-adjacency topology. We establish the first classification benchmark on the ResPlan corpus (17,107 vector floor plans; 162,755 rooms; six categories) under a strict plan-level split. VF-GraphSAGE attains 97.92 ± 0.06% accuracy and 97.93 ± 0.05% macro-F1, significantly outperforming rule-based, classic machine-learning, and GNN baselines (p < 10 -16 ). Controlled ablations attribute the gain specifically to the polygon vertex encoding. We release code, weights, and the full evaluation protocol.

Zitieren

APA

Ghoddusifar, S. H. (2026). VF-GraphSAGE: Vertex feature-enhanced graph neural network for room classification in residential floor plans. International Journal of Architectural Computing. https://doi.org/10.1177/14780771261500170

Vancouver

Ghoddusifar SH. VF-GraphSAGE: Vertex feature-enhanced graph neural network for room classification in residential floor plans. International Journal of Architectural Computing. 2026. doi:10.1177/14780771261500170

BibTeX
@article{Ghoddusifar2026,
  author = {Ghoddusifar, S. Hadi},
  title = {VF-GraphSAGE: Vertex feature-enhanced graph neural network for room classification in residential floor plans},
  journal = {International Journal of Architectural Computing},
  year = {2026},
  doi = {10.1177/14780771261500170}
}
Kostenlos starten →