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

Diffusion-aware graph refinement for graph-level classification and property detection

delete2025-11-18
delete0
PRE
AI
S
Seyedeh Fatemeh Mousavi
M
Mohammad Rahmati *
M
Mostafa Haghir Chehreghani
DOI：10.1016/j.engappai.2025.113157delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
• DAGR refines collections of small graphs for graph-level tasks. • Reveals global long-range dependencies beyond local neighborhoods via diffusion. • Drop-in for existing embedding methods; no changes to downstream models. • Enhances detection of connectivity, bipartiteness, triangle-freeness. • Improves graph-level classification accuracy by up to about 9 percentage points.

Journal

Engineering Applications of Artificial Intelligence cover
Engineering Applications of Artificial Intelligence
IF:
8
Papers:
5.3K
Citations:
3.5W

Organization

No organization information available