Heterogeneous graph convolutional network pre-training as side information for improving recommendation

For the recommendation domain, most of the existing integrated graph neural network (GNN)-based architectures have still much focused on encoding the associated extra side information in forms of heterogeneous information network (HIN). Then, it is simultaneously utilized in multiple fine-tuning processes to effectively learn preferences from user-item interaction data which might require tremendous computational efforts. In addition, these approaches have also failed to incorporate with previous learnt and transferable knowledge from pre-trained models to better fine-tune for recommendation task. To meet these challenges, in this paper we propose a novel heterogeneous graph neural architecture, named: PreHIN4Rec. The proposed PreHIN4Rec is considered as the graph pre-training approach for leveraging the performance of recommendation task in both accuracy and scalability aspects. In general, our proposed PreHIN4Rec is designed to efficiently preserve both heterogeneous schematic and local structural latent features of user-item interactions in forms of HINs. It can effectively support to better fine-tune for achieving remarkable improvements in recommendation tasks through integrating with existing recommendation frameworks. The extensive experiments in benchmark datasets demonstrate the effectiveness of our proposed PreHIN4Rec model in comparing with recent state-of-the-art GNN-based recommendation baselines.