GAHNE: Graph-Aggregated Heterogeneous Network Embedding

TL;DR

GAHNE is a novel method for embedding heterogeneous information networks that effectively aggregates semantic information from various sub-networks and global data, leading to improved performance in downstream tasks.

Contribution

The paper introduces GAHNE, a new model that automatically captures comprehensive semantics of HINs without manual meta-path design, enhancing embedding quality.

Findings

GAHNE outperforms state-of-the-art methods on three real-world datasets.

The model effectively integrates local and global network information.

Experiments demonstrate consistent improvements in downstream tasks.

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.