logo
CanyamAI summaries for academic research
language
MobileMobile
  • Phone FeatureWeChat Mini Program
EnglishEnglish
noticeNotice
BlogBlog
delete
arrow
Return

Scalable multi-objective graph layout via phase-wise optimizations

delete2026-09-08
delete0
PRE
AI
Y
Yilei He
J
Jiansu Pu *
C
Chengjin Shi
Z
Zheng Miao
H
Hao Jia
DOI：10.1016/j.knosys.2026.116998delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
• PMO turns multi-objective graph layout from loss weighting into phase-wise execution. • PMO optimizes one aesthetic objective per phase instead of all losses at each step. • GVLM-PMO lowers training time, memory usage, and FLOPs over joint optimization. • Objective-count analysis shows runtime is relatively insensitive to increasing objectives. • GVLM-PMO preserves competitive layout quality with lower resource cost.
Keywords:
Graph layout
Graph neural networks
Training strategy
Multi-objective optimization

Journal

K
Knowledge-Based Systems
IF:
7.6
Papers:
1.2W
Citations:
4.5W

Organization

No organization information available