IEA-GNN: Anchor-aware graph neural network fused with information entropy for node classification and link prediction

Graph neural networks are essential in mining complex relationships in graphs. However, most methods ignore the global location information of nodes and the discrepancy between symmetrically located nodes, resulting in the inability to distinguish between nodes with homogeneous network neighborhoods. We propose an Anchor-aware Graph Neural Network fused with Information Entropy (IEA-GNN) to capture the global location information of nodes in the graph. IEA-GNN first calculates the information entropy of nodes and constructs candidate sets of anchors. We define the calculation method of the distance from any node to the anchor points and incorporate the relative distance information between nodes at initialization. The nonlinear distance-weighted aggregation learning strategy based on the anchor points of candidate sets is used to obtain the nodes' feature information, which can be captured more effectively by fusing the global location information to the node representation with the selected anchor points. Selecting anchor points based on information entropy avoid the aggregation of anchor points in the graph, highlighting the positional differences between nodes and making it easier to distinguish homogeneous neighborhood nodes. Experimental results of node classification and link prediction on five datasets show that IEA-GNN outperforms the baseline model.