Progressive Community Merging Cooperative Coevolution Algorithm for Influence Blocking Maximization in Social Networks

Abstract

The widespread adoption of online social networks (OSNs) has facilitated social interaction and knowledge dissemination while raising concerns about extensive negative information propagation. Competitive propagation of positive and negative information can mitigate negative impacts. Influence blocking maximization (IBM) identifies a set of nodes initiating positive information propagation in OSNs to maximize blocking negative influence. This paper first introduces an effective influence blocking estimator (DPADV) that replaces computationally expensive Monte Carlo simulations. DPADV can calculate the approximate diffusion value for nodes activated by negative information in any hop neighborhood. Meanwhile, to address the challenges of complexity and computational efficiency brought about by the continuous expansion of OSNs, we propose the progressive community merging cooperative coevolution (PCMCC) algorithm. PCMCC divides the search space into communities and initializes a subpopulation for each community. Each subpopulation is responsible for optimizing a community, thereby implementing a divide-and-conquer approach. To enhance collaboration among communities and global exploration, we employed a progressive community merging strategy, supplemented by multi-population evolution strategies to guide the search towards global optima. Additionally, we developed an efficient heuristic metric for evaluating node importance, which is used to design population crossover and local search in the evolutionary scheme. Experimental results on six real-world and four synthetic networks demonstrate that PCMCC exhibits competitive performance compared to state-of-the-art algorithms, achieving near-greedy performance with lower time complexity.