Metraipolis › archive › dc_68b2ebd86ece

Inductive Graph Layout with Implicit Neural Fields — arXiv:2608.08876

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.08876
License (as archived)
CC0-1.0
Archived
2026-10-19T08:59:37.651Z
SHA-256 of the archived text
ae8bcce34522913d3a535bbc269edba6f126a41304ea53b7e26d60f5c31d8ab6
Stable URL of this page
https://metraipolis.com/documento/dc_68b2ebd86ece

How to cite

Inductive Graph Layout with Implicit Neural Fields — arXiv:2608.08876 — arXiv (en), https://arxiv.org/abs/2608.08876 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_68b2ebd86ece (Metraipolis archive dc_68b2ebd86ece, sha256 ae8bcce34522913d3a535bbc269edba6f126a41304ea53b7e26d60f5c31d8ab6)
BibTeX
@misc{dc68b2ebd86ece,
  title = {Inductive Graph Layout with Implicit Neural Fields — arXiv:2608.08876},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.08876},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_68b2ebd86ece; sha256 ae8bcce34522913d3a535bbc269edba6f126a41304ea53b7e26d60f5c31d8ab6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.08876. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

A graph layout is normally a table of $N$ free coordinates. We optimise a function with a fixed number of parameters instead. This gives a drawing a sample complexity and an extensible domain. Force-directed algorithms remain the standard tools for graph drawing. The most accurate among them minimise stress in the Kamada-Kawai formulation by directly optimising the node coordinates, at a full objective cost of $O(N^2)$ in time and space. Here, we propose Fling (Field Layout via Implicit Neural Geometry), a small neural network mapping the distances of each node to a set of landmarks, positioning it in the plane by training on the layout energy. The full spring system then becomes tractable without its distance matrix, as rest lengths follow from a landmark bound in constant time per pair while a second network learns the majorisation sums from exact anchor rows, at $O(|\mathcal{A}|N)$ per step for $|\mathcal{A}|\ll N$ anchors. Unlike neural drawers that read the graph by message passing, we represent the drawing as a function of node features. An unseen node costs one forward pass, where sparse and low-rank majorisation remain transductive. As the unknowns are weights rather than coordinates, the energy only requires a small fraction of the nodes, and a field fitted that way outperforms PivotMDS, landmark MDS, and a kernel ridge trained on the same energy and features, when the task is fitting the energy of a graph from a sample of its nodes. In addition, the same parameterisation enables a stochastic pivot stress variant, an aesthetics-optimised variant carrying a neighbour-embedding energy with node-edge clearance and crossing terms on the same field, and conditioning on the weight between two energies gives a whole layout family from one run.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-11 in cs.HC).
Categorie arXiv: Human-Computer Interaction (cs.HC) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.08876 — 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 2026-10-19T08:54:56.009Z dalla pagina https://arxiv.org/catchup/cs.HC/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).