返回
A multi-scale graph embedding method via multiple corpora
DOI:10.1016/j.neucom.2023.03.053.png)
摘要
En 中文
Graph embedding aims at learning continuous vector representations for graphs which is crucial for graph analytics. Natural Language Process (NLP)-based graph embedding methods build corpus for graph data by treating substructures as words and then use NLP models to learn graph embeddings. However, the size difference and data redundancy among substructures are less explored in the built corpora. To mitigate this problem, we propose an unsupervised multi-scale graph embedding method. To be a speci-fic, we first build multiple graph corpora for a graph dataset, where each corpus only contains substruc-tures of specific granularity. Then, we extend a document embedding model to each graph corpus to obtain graph embeddings of different scales. At last, we obtain the final multi-scale embedding of a graph by pooling its multiple embeddings. Comprehensive experiments on real graph datasets indicate that the proposed method obtains competitive results with state-of-the-arts, and is superior to some classic graph kernels and graph embedding methods on six out of ten benchmark datasets. (c) 2023 Published by Elsevier B.V.
Keyword:
Graph embedding
Corpus
Multi-scale
Subtree pattern
期刊
IF:
6.5
论文数:
2.5W
被引数:
6.5W
机构
引用论文
Productivity enhancement of solar still by PCM and Nanoparticles miscellaneous basin absorbing materials
Desalination
IF0
Graph classification based on structural features of significant nodes and spatial convolutional neural networks基于显著节点结构特征和空间卷积神经网络的图分类
NEUROCOMPUTING
IF6.5
Social network analysis: Characteristics of online social networks after a disaster社会网络分析: 灾后在线社会网络的特征
Environmental Factors and Seasonality Affect the Concentration of Rotundone in Vitis vinifera L. cv. Shiraz Wine
PLOS ONE
IF0

