Network Embedding With Completely-Imbalanced Labels
Network Embedding With Completely-Imbalanced Labels
复制标题
具有完全不平衡标签的网络嵌入
DOI：
10.1109/tkde.2020.2971490
复制
发表时间：
2021
影响因子：
8.9
通讯作者：
Yu Philip S.
中科院分区：
文献类型：
--
作者：
Zheng Wang;Ye Xiaojun;Wang Chaokun;Cui Jian;Yu Philip S.
网络嵌入旨在将网络投射到低维空间中，正日益成为网络研究的热点。半监督网络嵌入利用了标记数据，并显示出良好的性能。然而，现有的半监督方法在完全不平衡的标签设置下会得到令人不满意的结果，其中一些类根本没有标记节点。为了解决这个问题，我们提出了两种新颖的半监督网络嵌入方法。第一个是名为RSDNE的浅层方法。具体来说，为了从完全不平衡的标签中获益，RSDNE以近似的方式保证了类内相似性和类间不相似性。另一种方法是RECT，它是一类新的图神经网络。与RSDNE不同的是，为了利用完全不平衡的标签，RECT挖掘了类语义知识。这使RECT能够处理具有节点特性和多标签设置的网络。在多个实际数据集上的实验结果证明了所提方法的优越性。
Network embedding, aiming to project a network into a low-dimensional space, is increasingly becoming a focus of network research. Semi-supervised network embedding takes advantage of labeled data, and has shown promising performance. However, existing semi-supervised methods would get unappealing results in the completely-imbalanced label setting where some classes have no labeled nodes at all. To alleviate this, we propose two novel semi-supervised network embedding methods. The first one is a shallow method named RSDNE. Specifically, to benefit from the completely-imbalanced labels, RSDNE guarantees both intra-class similarity and inter-class dissimilarity in an approximate way. The other method is RECT which is a new class of graph neural networks. Different from RSDNE, to benefit from the completely-imbalanced labels, RECT explores the class-semantic knowledge. This enables RECT to handle networks with node features and multi-label setting. Experimental results on several real-world datasets demonstrate the superiority of the proposed methods.