LayoutGKN: Graph Similarity Learning of Floor Plans
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914020350492672 |
|---|---|
| author | van Engelenburg, Casper van Gemert, Jan Khademi, Seyran |
| author_facet | van Engelenburg, Casper van Gemert, Jan Khademi, Seyran |
| contents | Floor plans depict building layouts and are often represented as graphs to capture the underlying spatial relationships. Comparison of these graphs is critical for applications like search, clustering, and data visualization. The most successful methods to compare graphs \ie, graph matching networks, rely on costly intermediate cross-graph node-level interactions, therefore being slow in inference time. We introduce \textbf{LayoutGKN}, a more efficient approach that postpones the cross-graph node-level interactions to the end of the joint embedding architecture. We do so by using a differentiable graph kernel as a distance function on the final learned node-level embeddings. We show that LayoutGKN computes similarity comparably or better than graph matching networks while significantly increasing the speed. \href{https://github.com/caspervanengelenburg/LayoutGKN}{Code and data} are open. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_03737 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LayoutGKN: Graph Similarity Learning of Floor Plans van Engelenburg, Casper van Gemert, Jan Khademi, Seyran Computer Vision and Pattern Recognition Floor plans depict building layouts and are often represented as graphs to capture the underlying spatial relationships. Comparison of these graphs is critical for applications like search, clustering, and data visualization. The most successful methods to compare graphs \ie, graph matching networks, rely on costly intermediate cross-graph node-level interactions, therefore being slow in inference time. We introduce \textbf{LayoutGKN}, a more efficient approach that postpones the cross-graph node-level interactions to the end of the joint embedding architecture. We do so by using a differentiable graph kernel as a distance function on the final learned node-level embeddings. We show that LayoutGKN computes similarity comparably or better than graph matching networks while significantly increasing the speed. \href{https://github.com/caspervanengelenburg/LayoutGKN}{Code and data} are open. |
| title | LayoutGKN: Graph Similarity Learning of Floor Plans |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.03737 |