期刊
NEURAL NETWORKS
卷 132, 期 -, 页码 180-189出版社
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.neunet.2020.08.021
关键词
Multi-view networks; Attention; Graph embedding
资金
- National Key Research and Development Program of China [2017YFB0802200]
- Fundamental Research Funds for Central Universities
- Innovation Fund of Xidian University
- China Scholarship Council [CSC201906960040]
Multi-view graph embedding is aimed at learning low-dimensional representations of nodes that capture various relationships in a multi-view network, where each view represents a type of relation-ship among nodes. Multitudes of existing graph embedding approaches concentrate on single-view networks, that can only characterize one simple type of proximity relationships among objects. However, most of the real-world complex systems possess multiple types of relationships among entities. In this paper, a novel approach of graph embedding for multi-view networks is proposed, named Multi-view Graph Attention Networks (MGAT). We explore an attention-based architecture for learning node representations from each single view, the network parameters of which are constrained by a novel regularization term. In order to collaboratively integrate multiple types of relationships in different views, a view-focused attention method is explored to aggregate the view wise node representations. We evaluate the proposed algorithm on several real-world datasets, and it demonstrates that the proposed approach outperforms existing state-of-the-art baselines. (c) 2020 Elsevier Ltd. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据