Weak Supervision Network Embedding for Constrained Graph Learning-猫眼课题宝

DOI：

10.1007/978-3-030-75762-5_39

发表时间：

2021

期刊：

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

Ting Guo;Xingquan Zhu;Yang Wang;Fang Chen

约束学习是一种弱监督学习任务，其目的是将领域约束融入到学习模型中，而不需要为每个实例添加标签。由于弱监督知识有用且容易获得，约束学习在性能上优于无监督学习，在标记代价方面优于监督学习。到目前为止，约束学习，特别是约束聚类已经得到了广泛的研究，但主要集中在欧氏空间的数据上。提出了一种用于图的约束学习的弱监督网络嵌入(WSNE)算法。由于单个节点没有标签，我们提出了一种新的损失函数来量化基于约束的损失，并将这种损失集成到一个图卷积神经网络(GCN)和变分图自动编码器(VGAE)的组合框架中，以联合建模图结构和节点属性。联合优化使WSNE学习嵌入不仅能保持网络的拓扑和内容，而且能满足约束条件。实验表明，在约束图学习任务中，WSNE的性能优于基线，包括约束图聚类和约束图分类。

Constrained learning, a weakly supervised learning task, aims to incorporate domain constraints to learn models without requiring labels for each instance. Because weak supervision knowledge is useful and easy to obtain, constrained learning outperforms unsupervised learning in performance and is preferable than supervised learning in terms of labeling costs. To date, constrained learning, especially constrained clustering, has been extensively studied, but was primarily focused on data in the Euclidean space. In this paper, we propose a weak supervision network embedding (WSNE) for constrained learning of graphs. Because no label is available for individual nodes, we propose a new loss function to quantify the constraint-based loss, and integrate this loss in a graph convolutional neural network (GCN) and variational graph auto-encoder (VGAE) combined framework to jointly model graph structures and node attributes. The joint optimization allows WSNE to learn embedding not only preserving network topology and content, but also satisfying the constraints. Experiments show that WSNE outperforms baselines for constrained graph learning tasks, including constrained graph clustering and constrained graph classification.

Weak Supervision Network Embedding for Constrained Graph Learning

文献摘要

相似文献