High-order graph attention network

GCN is a widely-used representation learning method for capturing hidden features in graph data. However, traditional GCNs suffer from the over-smoothing problem, hindering their ability to extract high-order information and obtain robust data representation. To overcome this limitation, we propose a novel graph model, the high-order graph attention network. Compared to other existing graph attention networks, our model can adaptively aggregate node features from multi-hop neighbors through an attention mechanism. Moreover, the edges in the original graph may not accurately represent the relationships between nodes. We implement a new approach to update the graph by using the aggregated node representation to adjust the edges with small step sizes. Additionally, we perform a theoretical analysis to demonstrate the relationships between our proposed model and other GCN models. Finally, we evaluate our proposed model against eight variants of GCN models on multiple widely-used benchmark datasets. The experimental results show the superiority of our proposed model over other models.

Automated summary

Traditional GCNs have the over-smoothing problem, limiting their ability to extract high-order information and obtain robust data representation. To address this issue, we propose a novel high-order graph attention network that adaptively aggregates node features from multi-hop neighbors through an attention mechanism. We also update the graph by adjusting the edges with small step sizes using the aggregated node representation. Theoretical analysis demonstrates the relationships between our proposed model and other GCN models, and experimental results show the superiority of our proposed model over other models.