RHCO: A Relation-aware Heterogeneous Graph Neural Network with Contrastive Learning for Large-scale Graphs

TL;DR

RHCO introduces a relation-aware heterogeneous graph neural network utilizing contrastive learning and positive sample selection to improve large-scale graph representations, outperforming existing models in academic datasets.

Contribution

The paper proposes a novel RHCO model that combines relation-awareness, contrastive learning, and positive sample selection for scalable large-scale heterogeneous graph learning.

Findings

RHCO achieves state-of-the-art performance on large-scale academic datasets.

Contrastive learning enhances the quality of node embeddings in heterogeneous graphs.

Positive sample selection improves the effectiveness of the learning process.

Abstract

Heterogeneous graph neural networks (HGNNs) have been widely applied in heterogeneous information network tasks, while most HGNNs suffer from poor scalability or weak representation when they are applied to large-scale heterogeneous graphs. To address these problems, we propose a novel Relation-aware Heterogeneous Graph Neural Network with Contrastive Learning (RHCO) for large-scale heterogeneous graph representation learning. Unlike traditional heterogeneous graph neural networks, we adopt the contrastive learning mechanism to deal with the complex heterogeneity of large-scale heterogeneous graphs. We first learn relation-aware node embeddings under the network schema view. Then we propose a novel positive sample selection strategy to choose meaningful positive samples. After learning node embeddings under the positive sample graph view, we perform a cross-view contrastive learning to obtain the final node representations. Moreover, we adopt the label smoothing technique to boost the performance of RHCO. Extensive experiments on three large-scale academic heterogeneous graph datasets show that RHCO achieves best performance over the state-of-the-art models.