基于关系嵌入的异质图神经网络链接预测模型

A Heterogeneous Graph Neural Network Link Prediction Model based on Relational Embedding

摘要:

异质图链接预测任务是一个具有挑战的任务；通过异质图神经网络可以学习异质图节点的节点表示，并基于链接端点的节点表示进行链接预测；为了解决基于元路径的异质图神经网络往往不能兼顾效率和性能而传统的基于关系的异质图模型难以处理复杂的关系抑或不能充分学习异质图中的类型信息的问题，提出了一种简单、轻量的基于关系嵌入的异质图神经网络链接预测模型 LightREGNN；使用可学习的关系嵌入表征图中的异质类型信息，并采用 TTPP 模型结构从而缓解模型退化问题；还采用了跳跃链接，L2归一化等方法进一步提升模型性能；通过可靠的实验表明，提出的LightREGNN 在异质图链接预测任务上相较于经典的基于节点表示的异质图链接预测模型有着更好的表现；平衡了模型的效率和性能，能够成为异质图链接预测任务上一个合适的候选模型。

关键词:图神经网络;链接预测;异质图;异质网络;关系嵌入

Abstract:

In the domain of graph analytics, the task of link prediction in heterogeneous graphs remains a formidable challenge. Heterogeneous Graph Neural Networks (HGNNs) have been developed to learn representations of nodes within such graphs, which are then used to predict links based on the representations of the nodes at the endpoints of those links. However, a significant issue arises with metapath-based HGNNs, which often cannot adequately balance efficiency with performance. Additionally, traditional relation-based heterogeneous graph models struggle to process complex relations or to fully learn and leverage the type information embedded in heterogeneous graphs.To address these limitations, we propose a novel, streamlined model designed for link prediction in HGNNs, termed LightREGNN. This model utilizes learnable relational type embeddings to characterize the heterogeneous type information present in graphs. By adopting the structural design of the TTPP model, LightREGNN effectively alleviates the problem of model degradation.Moreover, the model incorporates innovative strategies such as jumping links and L2 normalization to further enhance its performance capabilities. Through rigorous experimental validation, it is demonstrated that LightREGNN outperforms classical node representation based models for link prediction in heterogeneous graphs. Our findings indicate that LightREGNN presents a more favorable trade-off between efficiency and performance, making it a suitable candidate for heterogeneous graph neural network applications with an emphasis on link prediction tasks.

Key words:graph neural networks; link prediction; heterogeneous graphs; heterogeneous networks; Relation Embedding