嵌入
计算机科学
节点(物理)
同种类的
理论计算机科学
关系(数据库)
关系数据库
图形
转化(遗传学)
数据挖掘
人工智能
数学
生物化学
结构工程
基因
组合数学
工程类
化学
作者
Ming-Han Feng,Chin-Chi Hsu,Cheng–Te Li,Mi-Yen Yeh,Shou-De Lin
出处
期刊:
日期:2019-05-13
卷期号:: 470-479
被引量:30
标识
DOI:10.1145/3308558.3313715
摘要
Network embedding aims at learning an effective vector transformation for entities in a network. We observe that there are two diverse branches of network embedding: for homogeneous graphs and for multi-relational graphs. This paper then proposes MARINE, a unified embedding framework for both homogeneous and multi-relational networks to preserve both the proximity and relation information. We also extend the framework to incorporate existing features of nodes in a graph, which can further be exploited for the ensemble of embedding. Our solution possesses complexity linear to the number of edges, which is suitable for large-scale network applications. Experiments conducted on several real-world network datasets, along with applications in link prediction and multi-label classification, exhibit the superiority of our proposed MARINE.
科研通智能强力驱动
Strongly Powered by AbleSci AI