Transfer Learning for Dynamic Community Knowledge Detection Based on Dual-Population Cooperation and Competition

Extracting evolving communities in social networks has attracted much attention recently due to its usefulness in the area of social media. Most existing models assume that network structures evolve monotonically and fail to leverage the fluctuating variation in the real world. Moreover, it is difficult to extract valuable community knowledge from previous snapshots, leading to a negative transfer to the current snapshot. In this article, we design a novel transferring strategy for dynamic community detection based on dual-population cooperation and competition. The transfer strategy guides the search by leveraging the meaningful community structures among previous snapshots based on the similarity between the current and all previous ones. Furthermore, to avoid the problem of insufficient population diversity caused by previous single-population algorithms, this article utilizes dual-population cooperative competition for multiobjective optimization. An intercooperation method effectively interchanges information according to normalized mutual information of different individuals in dual-population. Each population optimizes according to different objectives with a role-oriented teaching–learning-based optimizer to compensate for defects such as many hyperparameters, declining diversity, and insufficient convergence. Top students integrate the fine-grained strategy to mutate boundary nodes depending on embedding-based node activity; Ordinary students fuse the coarse-grained method to separate loosely connected subcommunities, while the bottom students do normal learning. Experimental results indicate that our approach outperforms state-of-the-art methods with high consistency.