计算机科学
透视图(图形)
链接(几何体)
边距(机器学习)
图形
人工智能
代表(政治)
理论计算机科学
联动装置(软件)
机器学习
骨料(复合)
节点(物理)
关系(数据库)
数据挖掘
计算机网络
生物化学
化学
材料科学
结构工程
政治
政治学
法学
复合材料
基因
工程类
作者
Anasua Mitra,Priyesh Vijayan,Sanasam Ranbir Singh,Diganta Goswami,Srinivasan Parthasarathy,Balaraman Ravindran
标识
DOI:10.1109/icdm54844.2022.00046
摘要
In this work, we present a novel approach for link prediction on heterogeneous networks – networks that accommodate multiple types of nodes as well as multiple types of relations among them. Specifically, we propose a multi-view network representation learning framework to incorporate structural intuitions from the underlying graph and enrich the relational representations for link prediction. The method relies on the metapath view, the community view, and the subgraph view between a source and target node pair whose linkage is to be predicted. Furthermore, our proposed model leverages a relation-aware attention mechanism to aggregate the candidate contexts in a principled way. Empirically, we demonstrate that the proposed architecture outperforms state-of-the-art transductive and inductive methods in link prediction by a significant margin. A detailed ablation study and attention weight visualizations suggest that the chosen views are complementary and useful to predict links robustly.
科研通智能强力驱动
Strongly Powered by AbleSci AI