HAHE: Hierarchical Attentive Heterogeneous Information Network Embedding
arXiv: Social and Information Networks, 2019.
Given the intractability of large scale HIN, network embedding which learns low dimensional proximity-preserved representations for nodes in the new space becomes a natural way to analyse HIN. However, two challenges arise in HIN embedding. (1) Different HIN structures with different semantic meanings play different roles in capturing rel...More
PPT (Upload PPT)