.png){kind=icon}
返回
Portable network resolving huge-graph isomorphism problem
.png){kind=icon}
OA
AI
DOI：10.1088/2632-2153/ad7d5f.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The graph isomorphism, as a key task in graph data analysis, is of great significance for the understanding, feature extraction, and pattern recognition of graph data. The best performance of traditional methods is the quasi-polynomial time complexity, which is infeasible for huge graphs. This paper aims to propose a lightweight graph network to resolve the problem of isomorphism in huge graphs. We propose a partitioning algorithm with linear time complexity based on isomorphic necessary condition to handle network graphs that cannot be fully computed by a single computer. We use anti-weight convolution analysis and skip connections to obtain a more stable representation with fewer layers and parameters. We implement simulations on personal computer (PC) with graphs consisting of hundred millions of edges, demonstrating the identification performance ( >98%) and time efficiency.
Keyword:
portable network
huge-graph isomorphism problem
graph partition
graph representation
期刊
M
IF:
4.6
论文数:
1.1K
被引数:
3.4K
机构
引用论文
分享收藏Interpretation of Radio-Echo Returns from Internal Water Bodies in Variegated Glacier, Alaska, U.S.A.美国阿拉斯加杂色冰川内部水体的无线电回波回波解释OAAI
OAAI分享收藏Effects of polymer micro-structures on the thermo-optical properties of a flexible soft-mater film based on liquid crystals / polymer composite.png)
Polymer
PolymerIF0
PREAI
分享收藏
分享收藏分享收藏XGraphBoost: Extracting Graph Neural Network-Based Features for a Better Prediction of Molecular PropertiesXGraphBoost: 提取基于图神经网络的特征以更好地预测分子特性
PREAI
分享收藏
查看更多内容