Swarm intelligence is the collective behavior emerging in systems with locally interacting components. Because of their self-organization capabilities, swarm-based systems show essential properties for handling real-world problems, such as robustness, scalability, and flexibility. Yet, we fail to understand why swarm-based algorithms work well, and neither can we compare the various approaches in the literature. The absence of a common framework capable of characterizing these several swarm-based algorithms, transcending their particularities, has led to a stream of publications inspired by different aspects of nature without a systematic comparison over existing approaches. Here we address this gap by introducing a network-based framework—the swarm interaction network—to examine computational swarm-based systems via the optics of the social dynamics. We investigate the structure of social interaction in four swarm-based algorithms, showing that our approach enables researchers to study distinct algorithms from a common viewpoint. We also provide an in-depth case study of the Particle Swarm Optimization, revealing that different communication schemes tune the social interaction in the swarm, controlling the swarm search mode. With the swarm interaction network, researchers can study swarm algorithms as systems, removing the algorithm particularities from the analyses while focusing on the structure of the swarm social interaction.

中文翻译：

---

在群体智能算法中发现社交互动网络

群智能是具有局部交互组件的系统中出现的集体行为。基于群体的系统具有自组织功能，因此它们显示了处理诸如鲁棒性，可伸缩性和灵活性之类的现实问题的基本属性。然而，我们不明白为什么基于群体的算法效果很好，我们也无法比较文献中的各种方法。缺乏能够描述这几种基于群体的算法，超越其特殊性的通用框架，导致大量出版物受到自然界不同​​方面的启发，而没有与现有方法进行系统比较。在这里，我们通过引入基于网络的框架（群体交互网络）来解决这一差距，以通过社会动态的视角检查基于计算的群体系统。我们在四种基于群体的算法中研究了社交互动的结构，这表明我们的方法使研究人员能够从一个共同的角度研究不同的算法。我们还提供了粒子群优化的深入案例研究，揭示了不同的通信方案可以调整群体中的社交互动，从而控制群体搜索模式。借助群体互动网络，研究人员可以将群体算法作为系统进行研究，从分析中消除算法的特殊性，同时关注群体社交互动的结构。