AAAI Publications, Thirty-Second AAAI Conference on Artificial Intelligence

Font Size: 
RSDNE: Exploring Relaxed Similarity and Dissimilarity from Completely-Imbalanced Labels for Network Embedding
Zheng Wang, Xiaojun Ye, Chaokun Wang, Yuexin Wu, Changping Wang, Kaiwen Liang

Last modified: 2018-04-25

Abstract


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.

Keywords


network embedding; social networks; artificial intelligence

Full Text: PDF