GAHNE: Graph-Aggregated Heterogeneous Network Embedding

Abstract

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.

References in corpus (10)

• Semi-Supervised Classification with Graph Convolutional Networks
• Spectral Networks and Locally Connected Networks on Graphs
• MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embedding
• Attributed Social Network Embedding
• Gated Graph Sequence Neural Networks
• Meta-Path Guided Embedding for Similarity Search in Large-Scale Heterogeneous Information Networks
• BHIN2vec: Balancing the Type of Relation in Heterogeneous Information Network
• Multi-Stage Self-Supervised Learning for Graph Convolutional Networks on Graphs with Few Labels
• ActiveHNE: Active Heterogeneous Network Embedding
• SelfORE: Self-supervised Relational Feature Learning for Open Relation Extraction