Fully decentralized learning is gaining momentum for training AI models at the Internet's edge, addressing infrastructure challenges and privacy concerns. In a decentralized machine learning system, data is distributed across multiple nodes, with each node training a local model based on its respective dataset. The local models are then shared and combined to form a global model capable of making accurate predictions on new data. Our exploration focuses on how different types of network structures influence the spreading of knowledge - the process by which nodes incorporate insights gained from learning patterns in data available on other nodes across the network. Specifically, this study investigates the intricate interplay between network structure and learning performance using three network topologies and six data distribution methods. These methods consider different vertex properties, including degree centrality, betweenness centrality, and clustering coefficient, along with whether nodes exhibit high or low values of these metrics. Our findings underscore the significance of global centrality metrics (degree, betweenness) in correlating with learning performance, while local clustering proves less predictive. We highlight the challenges in transferring knowledge from peripheral to central nodes, attributed to a dilution effect during model aggregation. Additionally, we observe that central nodes exert a pull effect, facilitating the spread of knowledge. In examining degree distribution, hubs in Barabasi-Albert networks positively impact learning for central nodes but exacerbate dilution when knowledge originates from peripheral nodes. Finally, we demonstrate the formidable challenge of knowledge circulation outside of segregated communities.

翻译：全去中心化学习正逐渐成为在互联网边缘训练人工智能模型的主流方法，以解决基础设施挑战和隐私问题。在去中心化机器学习系统中，数据分布在不同节点上，每个节点基于其各自数据集训练本地模型。随后，本地模型被共享和组合，形成能够对全新数据做出准确预测的全局模型。我们的研究重点在于不同类型网络结构如何影响知识传播——即节点通过吸收网络中其他节点数据学习模式所获得的见解的过程。具体而言，本研究利用三种网络拓扑和六种数据分布方法，探讨网络结构与学习性能之间复杂的相互作用关系。这些方法考虑了不同节点属性，包括度中心性、介数中心性和聚类系数，以及节点在这些指标上呈现高值或低值的情况。我们的研究结果强调了全局中心性指标（度、介数）与学习性能的相关性，而局部聚类则预测能力较弱。我们揭示了知识从外围节点向中心节点传递的挑战，这归因于模型聚合过程中的稀释效应。此外，我们观察到中心节点会产生牵引效应，促进知识传播。在度分布分析中，Barabasi-Albert网络中的枢纽节点对中心节点的学习产生积极影响，但当知识源自外围节点时会加剧稀释效应。最后，我们证明了知识在隔离社区之外流动的严峻挑战。