RSDNE: Exploring Relaxed Similarity and Dissimilarity from Completely-Imbalanced Labels for Network Embedding
RSDNE: Exploring Relaxed Similarity and Dissimilarity from Completely-Imbalanced Labels for Network Embedding
复制标题
DOI：
10.1609/aaai.v32i1.11242
复制
发表时间：
2018-04
期刊：
影响因子：
--
通讯作者：
Zheng Wang;Xiaojun Ye;Chaokun Wang;Yuexin Wu;Changping Wang;Kaiwen Liang
中科院分区：
文献类型：
--
作者：
Zheng Wang;Xiaojun Ye;Chaokun Wang;Yuexin Wu;Changping Wang;Kaiwen Liang
网络嵌入技术旨在将网络投射到低维空间，正日益成为网络研究的热点。半监督网络嵌入利用了标签数据，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不理想的结果，其中一些类别根本没有标签节点。为了缓解这一问题，我们提出了一种新的半监督网络嵌入方法，称为松弛相似与相异网络嵌入(RSDNE)。具体地说，为了从完全不平衡的标签中获益，RSDNE以近似的方式同时保证了类内相似性和类间相异度。在几个真实数据集上的实验结果表明了该方法的优越性。
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 a novel semi-supervised network embedding method, termed Relaxed Similarity and Dissimilarity Network Embedding (RSDNE). Specifically, to benefit from the completely-imbalanced labels, RSDNE guarantees both intra-class similarity and inter-class dissimilarity in an approximate way. Experimental results on several real-world datasets demonstrate the superiority of the proposed method.