Heterogeneous Graph Representation Learning with Relation Awareness

Abstract

Representation learning on heterogeneous graphs aims to obtain meaningful node representations to facilitate various downstream tasks, such as node classification and link prediction. Existing heterogeneous graph learning methods are primarily developed by following the propagation mechanism of node representations. There are few efforts on studying the role of relations for improving the learning of more fine-grained node representations. Indeed, it is important to collaboratively learn the semantic representations of relations and discern node representations with respect to different relation types. To this end, in this paper, we propose a novel Relation-aware Heterogeneous Graph Neural Network, namely R-HGNN, to learn node representations on heterogeneous graphs at a fine-grained level by considering relation-aware characteristics. Specifically, a dedicated graph convolution component is first designed to learn unique node representations from each relation-specific graph separately. Then, a cross-relation message passing module is developed to improve the interactions of node representations across different relations. Also, the relation representations are learned in a layer-wise manner to capture relation semantics, which are used to guide the node representation learning process. Moreover, a semantic fusing module is presented to aggregate relation-aware node representations into a compact representation with the learned relation representations. Finally, we conduct extensive experiments on a variety of graph learning tasks, and experimental results demonstrate that our approach consistently outperforms existing methods among all the tasks.

arXiv commentAccepted by the TKDE journal

References in corpus (11)

• Adam: A Method for Stochastic Optimization
• Distributed Representations of Words and Phrases and their Compositionality
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• DeepWalk: Online Learning of Social Representations
• Inductive Representation Learning on Large Graphs
• Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting
• Neural Graph Collaborative Filtering
• Graph Convolutional Neural Networks for Web-Scale Recommender Systems
• MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embedding
• Representation Learning for Attributed Multiplex Heterogeneous Network
• Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning

Cited by in corpus (8)

• Graph Attention Multi-Layer Perceptron
• MECCH: Metapath Context Convolution-based Heterogeneous Graph Neural Networks
• HMSG: Heterogeneous Graph Neural Network based on Metapath Subgraph Learning
• Algorithm and System Co-design for Efficient Subgraph-based Graph Representation Learning
• Enabling Homogeneous GNNs to Handle Heterogeneous Graphs via Relation Embedding
• Towards Human-like Perception: Learning Structural Causal Model in Heterogeneous Graph
• Seq-HGNN: Learning Sequential Node Representation on Heterogeneous Graph
• Meta-Path Learning for Multi-relational Graph Neural Networks