Abstract: To improve the accuracy of node importance evaluation in opportunistic networks, a node embedding-based node importance evaluation method is proposed. Considering the time-varying nature of opportunistic networks, a time window aggregation graph is employed, so that network topology and temporal connection data can be obtained in the window. Graph attention mechanism is utilized to extract the topological features of nodes, and temporal encoding and self-attention mechanism are employed to capture temporal features of nodes. Node embedding vectors are achieved by integrating two features. The cluster importance for nodes is introduced and the transition probability matrix is constructed. The node importance is obtained by PageRank algorithm. On real opportunistic network datasets, experimental results demonstrate that the proposed method exhibits better evaluation accuracy compared to approaches such as f-PageRank and dynamic graph convolutional network.

Key words: opportunistic network ,  node importance ,  node embedding ,  self-attention mechanism ,  transition probability matrix