Homogenization with Explicit Semantics Preservation for Heterogeneous Information Network

Abstract

Heterogeneous information network (HIN), especially its embedding task, has drawn much attention recently as its rich latent information brings great benefits to complex classification and clustering. Many prior embedding works focus on designing a specific approach for the HIN while others implicitly homogenize the HIN with losing some semantic information. In this paper, a novel explicit homogenization method is proposed to preserve more semantic information, where the latent information of intermediate nodes among each meta-path instance and that among multiple meta-path instances are incorporated into the conventional adjacent matrix (or weight matrix). Then, the transfer of weight matrix and the fusion of node-level embeddings are considered to obtain graph-level embedding to solve the HIN problem. In such way, much more latent information of meta-path is preserved so that the proposed method exhibits its superiority in comparison to state-of-the-art works in classification and clustering tasks.