Network Embedding with Class Discriminability
Network embedding,which learns low-dimensional rep-resentations from networks for network information preser-vation,has gained considerable attention in recent years.Network embedding has been shown to outperform many traditional node representation learning methods on the tasks such as clustering,classification and visualization.However,focusing on preserving the proximity between nodes,most previous works ignore many prominent features of networks.Some recent methods contrive to preserve cluster(class)structure in network by making representations closer to each other for nodes in the same class and enhancing the dis-criminability of cluster structure,which can result in better performance on various tasks.In this paper,we propose a simple and general model which can be extended to most net-work embedding models,especially NMF-based methods,to make the representations more discriminative for preserving cluster structure and therefore improve their results.In the experiments,we employ our model to extend an original and basic algorithm dating back to the early 2000s as a simple example.Comparison results with state-of-the-art algorithms have confirmed the effectiveness of our model.
Network embedding feature learning dimension reduction class discriminability
Zi-Hua Li Ling Huang Kai Wang Chang-Dong Wang Wei Shi Dong Huang
Sun Yat-sen University Guangzhou,China South China Agricultural University Guangzhou,China
国际会议
2019国图灵大会(ACM Turing Celebration conference-China 2019 )
成都
英文
17-21
2019-05-17（万方平台首次上网日期，不代表论文的发表时间）