Identifying influential nodes based on hybrid centrality of receivers in the second-order dissemination

Abstract

Hybrid models for influential node identification have gained attention for integrating local, semilocal, and global information. These models regularly use location to account for global information, however, seldom take further consideration of the nonlinear feedback contribution and non-redundant bridging ability. In information dissemination, the nonlinear feedback contribution can enhance information reliability through diverse feedback validation, and the non-redundant bridging ability can foster broad access and allocation of heterogeneous information by connecting multiple independent nodes. Additionally, most hybrid models overlook centrality of receivers in the second-order dissemination, which can affect the scope and speed of information dissemination. Moreover, identification of bottom ranked nodes is often ignored, despite that the optimization of these nodes can enhance network efficiency. This work presents a novel hybrid model that incorporates hybrid centrality of receivers in the second-order dissemination. Specifically, hybrid centrality is formulated by simultaneously considering the location, nonlinear feedback contribution, and non-redundant bridging ability. Receivers in the second-order dissemination are then collected, and node importance is determined based on their hybrid centrality. Extensive experiments on 9 real-world and 3 synthetic networks show that our model outperforms state-of-the-art models in node ranking, top-k and bottom-k nodes identification. Robustness is also validated via varying infection probabilities.