Cross-view Self-Supervised Learning on Heterogeneous Graph Neural Network via Bootstrapping
This work addresses a bottleneck in self-supervised learning for heterogeneous graph neural networks, which is incremental but improves efficiency and performance in domains like social networks or recommendation systems.
The paper tackles the difficulty of generating high-quality positive and negative pairs for contrastive learning on heterogeneous graphs by introducing a bootstrapping-based self-supervised method that leverages network schema and meta-path views, achieving state-of-the-art performance on various real-world datasets.
Heterogeneous graph neural networks can represent information of heterogeneous graphs with excellent ability. Recently, self-supervised learning manner is researched which learns the unique expression of a graph through a contrastive learning method. In the absence of labels, this learning methods show great potential. However, contrastive learning relies heavily on positive and negative pairs, and generating high-quality pairs from heterogeneous graphs is difficult. In this paper, in line with recent innovations in self-supervised learning called BYOL or bootstrapping, we introduce a that can generate good representations without generating large number of pairs. In addition, paying attention to the fact that heterogeneous graphs can be viewed from two perspectives, network schema and meta-path views, high-level expressions in the graphs are captured and expressed. The proposed model showed state-of-the-art performance than other methods in various real world datasets.