Your browser doesn't support javascript.
loading
MECCH: Metapath Context Convolution-based Heterogeneous Graph Neural Networks.
Fu, Xinyu; King, Irwin.
Afiliação
  • Fu X; Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, China. Electronic address: xyfu@cse.cuhk.edu.hk.
  • King I; Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, China.
Neural Netw ; 170: 266-275, 2024 Feb.
Article em En | MEDLINE | ID: mdl-38000310
ABSTRACT
Heterogeneous graph neural networks (HGNNs) were proposed for representation learning on structural data with multiple types of nodes and edges. To deal with the performance degradation issue when HGNNs become deep, researchers combine metapaths into HGNNs to associate nodes closely related in semantics but far apart in the graph. However, existing metapath-based models suffer from either information loss or high computation costs. To address these problems, we present a novel Metapath Context Convolution-based Heterogeneous Graph Neural Network (MECCH). MECCH leverages metapath contexts, a new kind of graph structure that facilitates lossless node information aggregation while avoiding any redundancy. Specifically, MECCH applies three novel components after feature preprocessing to extract comprehensive information from the input graph efficiently (1) metapath context construction, (2) metapath context encoder, and (3) convolutional metapath fusion. Experiments on five real-world heterogeneous graph datasets for node classification and link prediction show that MECCH achieves superior prediction accuracy compared with state-of-the-art baselines with improved computational efficiency. The code is available at https//github.com/cynricfu/MECCH.
Assuntos
Palavras-chave

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Assunto principal: Redes Neurais de Computação / Aprendizagem Idioma: En Revista: Neural Netw Assunto da revista: NEUROLOGIA Ano de publicação: 2024 Tipo de documento: Article

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Assunto principal: Redes Neurais de Computação / Aprendizagem Idioma: En Revista: Neural Netw Assunto da revista: NEUROLOGIA Ano de publicação: 2024 Tipo de documento: Article