By “social learning,” in this article we refer to mechanisms for opinion formation and decision making over graphs and the study of how agents’ decisions evolve dynamically through interactions with neighbors and the environment. The study of social learning strategies is critical for at least two reasons. On one hand, it allows for a deeper understanding of the fundamental cognitive mechanisms that enable opinion formation over networks and the propagation of information or misinformation over them. On the other hand, these same learning strategies are effective for decision making by networked agents under challenging conditions, such as highly dynamic environments, nonstationary models and data, untruthful or malicious agents, sparsely connected graphs, and constrained communication. The article presents a unifying framework that covers several cases of interest, such as single-agent Bayesian learning, multiagent non-Bayesian learning, adaptive social learning, social machine learning, partial information sharing, influence discovery, and many others. The presentation highlights important limitations of the traditional social learning strategies. One limitation is the inability to track well drifting conditions. Traditional approaches lead to stubborn agents, which resist new states of information and are slow to react to changes in the environment, like an opinion that changes over time. Another limitation of the traditional strategies is that they assume perfect knowledge of the data models, which is seldom available in practice. The article illustrates recent advances that address these issues. We show how to endow multiagent networks with adaptation abilities and how to build social machine learning solutions that learn the necessary models directly from the data. These are fundamental steps toward the construction of socially intelligent networks, capable of exploiting cooperation and diversity across the agents to guarantee reliable learning performance under nonstationary, heterogeneous, and uncertain environments.

中文翻译：

---

Socially Intelligent Networks：基于图的决策框架


在本文中，我们所说的“社会学习”是指在图表上形成意见和决策的机制，以及研究代理的决策如何通过与邻居和环境的互动而动态演变。社会学习策略的研究至关重要，至少有两个原因。一方面，它允许更深入地理解基本的认知机制，这些机制使人们能够在网络上形成意见，并在网络上传播信息或错误信息。另一方面，这些相同的学习策略对于网络代理在具有挑战性的条件下做出决策是有效的，例如高度动态的环境、非平稳的模型和数据、不真实或恶意的代理、稀疏连接的图和受限的通信。本文提出了一个统一的框架，涵盖了几个感兴趣的案例，例如单智能体贝叶斯学习、多智能体非贝叶斯学习、自适应社交学习、社交机器学习、部分信息共享、影响发现等。该演示文稿强调了传统社交学习策略的重要局限性。一个限制是无法跟踪井漂移条件。传统方法会导致顽固的代理，这些代理会抵制新的信息状态，并且对环境的变化反应缓慢，例如随时间变化的观点。传统策略的另一个限制是它们假设对数据模型有完美的了解，而这在实践中很少可用。本文介绍了解决这些问题的最新进展。我们将展示如何赋予多智能体网络适应能力，以及如何构建直接从数据中学习必要模型的社交机器学习解决方案。 这些是构建社交智能网络的基本步骤，能够利用代理之间的合作和多样性，以保证在非平稳、异构和不确定环境中的可靠学习性能。