Multi-view Self-supervised Heterogeneous Graph Embedding
Multi-view Self-supervised Heterogeneous Graph Embedding
复制标题
DOI：
10.1007/978-3-030-86520-7_20
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Jianan Zhao;Qian Wen;Shiyu Sun;Yanfang Ye;Chuxu Zhang
中科院分区：
文献类型：
--
作者：
Jianan Zhao;Qian Wen;Shiyu Sun;Yanfang Ye;Chuxu Zhang
由于图的稀疏性和人工标注的高成本，图挖掘任务往往缺乏来自标记信息的监督。为了缓解这个问题，受自监督学习（SSL）在计算机视觉和自然语言处理方面的最新进展的启发，已经提出了图自监督学习方法，并通过利用未标记信息取得了显着的性能。然而，大多数现有的图SSL方法集中在同构图，忽略了现实世界中的节点和边是多种类型的普遍存在的异构性。因此，直接将现有的图SSL方法应用于异构图，不能完全捕获异构图中丰富的语义及其相关性。有鉴于此，我们研究了异构图上的自监督学习，并提出了一种新的模型多视图自监督异构图嵌入（MVSE）。MVSE通过对元路径定义的不同视图的信息进行编码，优化视图内和视图间的对比学习任务，综合利用未标记信息，学习节点嵌入。广泛的实验进行各种任务，以显示所提出的框架的有效性。
Graph mining tasks often suffer from the lack of supervision from labeled information due to the intrinsic sparseness of graphs and the high cost of manual annotation. To alleviate this issue, inspired by recent advances of self-supervised learning (SSL) on computer vision and natural language processing, graph self-supervised learning methods have been proposed and achieved remarkable performance by utilizing unlabeled information. However, most existing graph SSL methods focus on homogeneous graphs, ignoring the ubiquitous heterogeneity of real-world graphs where nodes and edges are of multiple types. Therefore, directly applying existing graph SSL methods to heterogeneous graphs can not fully capture the rich semantics and their correlations in heterogeneous graphs. In light of this, we investigate self-supervised learning on heterogeneous graphs and propose a novel model named Multi-View Self-supervised heterogeneous graph Embedding (MVSE). By encoding information from different views defined by meta-paths and optimizing both intra-view and inter-view contrastive learning tasks, MVSE comprehensively utilizes unlabeled information and learns node embeddings. Extensive experiments are conducted on various tasks to show the effectiveness of the proposed framework.