An effective heterogeneous information network representation learning framework

Given the heterogeneity of real-world networks and the low efficiency of directly mining networks, heterogeneous information network (HIN) representation learning, which learns low-dimensional embeddings of nodes to represent various structural and semantic information in HINs, becomes a very crucial topic. Existing HIN based representation learning methods either omit the global information of networks, or only consider the first-order neighbors of each node. The two problems reflect the insufficient extraction and exploitation of network information for HIN embedding. To address these problems, we propose a novel Heterogeneous Graph SAmple and aggreGatE framework, named HGSAGE, for learning low-dimensional similarity-preserved embeddings of nodes in HINs. This framework consists of three mechanisms, i.e., the gravity model based on the meta-path reachable graphs mechanism to capture the global information of HINs, the node-level sampling and aggregating mechanism to sample and incorporate features from immediate and mediate neighbors of nodes, and the semantic-level aggregating mechanism to combine embeddings with respect to different meta -paths. Extensive experiments on three real-world heterogeneous networks of different types and scales for multiple tasks show that the proposed framework significantly outperforms the baselines. Moreover, HGSAGE has important application values in this research field.& COPY; 2023 Elsevier B.V. All rights reserved.

Automated summary

Given the heterogeneity of real-world networks and the low efficiency of directly mining networks, learning low-dimensional embeddings of nodes in heterogeneous information networks (HINs) becomes crucial. In this paper, we propose a framework called HGSAGE for learning similarity-preserved embeddings of nodes in HINs. HGSAGE addresses the problems of omitting global information and considering only first-order neighbors by incorporating mechanisms to capture global information, sample and aggregate features from immediate and mediate neighbors, and combine embeddings from different meta-paths. Experimental results show that HGSAGE outperforms baseline methods on multiple tasks in real-world heterogeneous networks. Moreover, HGSAGE has important application values in this research field.