A multilayered approach for link prediction in heterogeneous complex networks

详细信息    查看全文

• 作者：Hadi Shakibian ^{h.shakibian@modares.ac.ir hadi.shakibian@modares.ac.ir}Author Vitae ; Nasrollah Moghadam Charkari ; ^{moghadam@modares.ac.ir}Author Vitae ; Saeed Jalili ^{sjalili@modares.ac.ir}Author Vitae
• 关键词：Heterogeneous complex networks ; Link prediction ; Meta-path ; LS-TSVM
• 刊名：Journal of Computational Science
• 出版年：2016
• 出版时间：November 2016
• 年：2016
• 卷：17
• 期：part_P1
• 页码：73-82
• 全文大小：1605 K
• 卷排序：17

文摘

We proposed a new supervised framework for link prediction in heterogeneous complex networks. We presented a multi-layered complex network model to generate a low computational proper set of meta-paths. Learning a number of link predictors based on different meta-paths and aggregating them leads to higher prediction accuracy.