IEICE TRANSACTIONS on Information
GRAPHULY: GRAPH U-Nets-Based Multi-Level Graph LaYout
Summary :
Graph layout is a critical component in graph visualization. This paper proposes GRAPHULY, a graph u-nets-based neural network, for end-to-end graph layout generation. GRAPHULY learns the multi-level graph layout process and can generate graph layouts without iterative calculation. We also propose to use Laplacian positional encoding and a multi-level loss fusion strategy to improve the layout learning. We evaluate the model with a random dataset and a graph drawing dataset and showcase the effectiveness and efficiency of GRAPHULY in graph visualization.
- Publication
- IEICE TRANSACTIONS on Information Vol.E105-D No.12 pp.2135-2138
- Publication Date
- 2022/12/01
- Publicized
- 2022/09/16
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2022EDL8050
- Type of Manuscript
- LETTER
- Category
- Computer Graphics
Authors
Kai YAN
Harbin Institute of Technology
Tiejun ZHAO
Harbin Institute of Technology
Muyun YANG
Harbin Institute of Technology
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Kai YAN, Tiejun ZHAO, Muyun YANG, "GRAPHULY: GRAPH U-Nets-Based Multi-Level Graph LaYout" in IEICE TRANSACTIONS on Information,
vol. E105-D, no. 12, pp. 2135-2138, December 2022, doi: 10.1587/transinf.2022EDL8050.
Abstract: Graph layout is a critical component in graph visualization. This paper proposes GRAPHULY, a graph u-nets-based neural network, for end-to-end graph layout generation. GRAPHULY learns the multi-level graph layout process and can generate graph layouts without iterative calculation. We also propose to use Laplacian positional encoding and a multi-level loss fusion strategy to improve the layout learning. We evaluate the model with a random dataset and a graph drawing dataset and showcase the effectiveness and efficiency of GRAPHULY in graph visualization.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2022EDL8050/_p
Copy
@ARTICLE{e105-d_12_2135,
author={Kai YAN, Tiejun ZHAO, Muyun YANG, },
journal={IEICE TRANSACTIONS on Information},
title={GRAPHULY: GRAPH U-Nets-Based Multi-Level Graph LaYout},
year={2022},
volume={E105-D},
number={12},
pages={2135-2138},
abstract={Graph layout is a critical component in graph visualization. This paper proposes GRAPHULY, a graph u-nets-based neural network, for end-to-end graph layout generation. GRAPHULY learns the multi-level graph layout process and can generate graph layouts without iterative calculation. We also propose to use Laplacian positional encoding and a multi-level loss fusion strategy to improve the layout learning. We evaluate the model with a random dataset and a graph drawing dataset and showcase the effectiveness and efficiency of GRAPHULY in graph visualization.},
keywords={},
doi={10.1587/transinf.2022EDL8050},
ISSN={1745-1361},
month={December},}
Copy
TY - JOUR
TI - GRAPHULY: GRAPH U-Nets-Based Multi-Level Graph LaYout
T2 - IEICE TRANSACTIONS on Information
SP - 2135
EP - 2138
AU - Kai YAN
AU - Tiejun ZHAO
AU - Muyun YANG
PY - 2022
DO - 10.1587/transinf.2022EDL8050
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E105-D
IS - 12
JA - IEICE TRANSACTIONS on Information
Y1 - December 2022
AB - Graph layout is a critical component in graph visualization. This paper proposes GRAPHULY, a graph u-nets-based neural network, for end-to-end graph layout generation. GRAPHULY learns the multi-level graph layout process and can generate graph layouts without iterative calculation. We also propose to use Laplacian positional encoding and a multi-level loss fusion strategy to improve the layout learning. We evaluate the model with a random dataset and a graph drawing dataset and showcase the effectiveness and efficiency of GRAPHULY in graph visualization.
ER -
English
