2020/12/23 by Xiaohe Li, Lijie Wen, Li, Xiaohe +6
Computer Science · #Advanced Graph Neural Networks #Aggregate (composite) #Artificial Intelligence (cs.AI) #Artificial intelligence #Computer science #Convolutional neural network #Domain Adaptation and Few-Shot Learning #Embedding #FOS: Computer and information sciences #Fuse (electrical) #Graph #Graph embedding #Heterogeneous network #Semantics (computer science) #Social and Information Networks (cs.SI) #Theoretical computer science #Topic Modeling #cs.AI #cs.SI
paper · pdf · doi:10.48550/arxiv.2012.12517
arxiv created 2020/12/23 · openalex publication_date 2020/12/23 · arxiv updated 2020/12/24 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
The real-world networks often compose of different types of nodes and edges with rich semantics, widely known as heterogeneous information network (HIN). Heterogeneous network embedding aims to embed nodes into low-dimensional vectors which capture rich intrinsic information of heterogeneous networks. However, existing models either depend on manually designing meta-paths, ignore mutual effects between different semantics, or omit some aspects of information from global networks. To address these limitations, we propose a novel Graph-Aggregated Heterogeneous Network Embedding (GAHNE), which is designed to extract the semantics of HINs as comprehensively as possible to improve the results of downstream tasks based on graph convolutional neural networks. In GAHNE model, we develop several mechanisms that can aggregate semantic representations from different single-type sub-networks as well as fuse the global information into final embeddings. Extensive experiments on three real-world HIN datasets show that our proposed model consistently outperforms the existing state-of-the-art methods.