Node importance evaluation in heterogeneous network based on attention mechanism and graph contrastive learning

Recently, heterogeneous networks have attracted widespread attention as a modeling approach for complex networks. However, the complex structure and diversity of semantic relations of heterogeneous networks pose challenges to node importance evaluation. In addition, existing methods use SIR model to set true labels for all nodes, which increases the complexity. In light of this, this paper proposes anode importance evaluation in heterogeneous network based on attention mechanism and graph contrastive learning method(AGCL). Specifically, AGCL contains two core parts: node embedding and node importance evaluation. Considering the complex structure of heterogeneous networks, node embedding employs graph contrastive learning to comprehensively extract structural features through neighbor and cross-domain views. Node importance evaluation integrates an attention mechanism to calculate the global and local importance of nodes separately. To reduce the complexity of setting the true labels, a subset of nodes is sampled based on the power-law distribution of node degrees for model training. The evaluation of AGCL is conducted in three real-world networks utilizing three metrics: the maximum connected subgraph node ratio, the maximum propagation range in the linear threshold model, and the maximum propagation range in the independent cascade model. The experiment results demonstrate that AGCL outperforms state-of-the-art techniques in evaluating node importance.