Fully decentralised federated learning enables collaborative training of
individual machine learning models on distributed devices on a network while
keeping the training data localised. This approach enhances data privacy and
eliminates both the single point of failure and the necessity for central
coordination. Our research highlights that the effectiveness of decentralised
federated learning is significantly influenced by the network topology of
connected devices. A simplified numerical model for studying the early
behaviour of these systems leads us to an improved artificial neural network
initialisation strategy, which leverages the distribution of eigenvector
centralities of the nodes of the underlying network, leading to a radically
improved training efficiency. Additionally, our study explores the scaling
behaviour and choice of environmental parameters under our proposed
initialisation strategy. This work paves the way for more efficient and
scalable artificial neural network training in a distributed and uncoordinated
environment, offering a deeper understanding of the intertwining roles of
network structure and learning dynamics.

去中心化联邦学习，在保持训练数据本地化的同时，能够在网络上分布式设备上进行个体机器学习模型的协作训练。我们的研究强调了去中心化联邦学习的有效性受连接设备的网络拓扑结构的显著影响。通过简化的数值模型研究这些系统的早期行为，我们得出了一种改进的人工神经网络初始化策略，利用底层网络节点的特征向量中心性分布，大大提高训练效率。此外，我们的研究还探索了在我们提出的初始化策略下的可扩展行为和环境参数的选择。这项工作为在分布式和非协调环境中进行更高效、可扩展的人工神经网络训练铺平了道路，并深入了解了网络结构和学习动力之间的相互作用。

分散式联邦学习中的初始化与拓扑效果

Initialisation and Topology Effects in Decentralised Federated Learning

Federated Learning (FL) is a well-known framework for successfully performing
a learning task in an edge computing scenario where the devices involved have
limited resources and incomplete data representation. The basic assumption of
FL is that the devices communicate directly or indirectly with a parameter
server that centrally coordinates the whole process, overcoming several
challenges associated with it. However, in highly pervasive edge scenarios, the
presence of a central controller that oversees the process cannot always be
guaranteed, and the interactions (i.e., the connectivity graph) between devices
might not be predetermined, resulting in a complex network structure. Moreover,
the heterogeneity of data and devices further complicates the learning process.
This poses new challenges from a learning standpoint that we address by
proposing a communication-efficient Decentralised Federated Learning (DFL)
algorithm able to cope with them. Our solution allows devices communicating
only with their direct neighbours to train an accurate model, overcoming the
heterogeneity induced by data and different training histories. Our results
show that the resulting local models generalise better than those trained with
competing approaches, and do so in a more communication-efficient way.

在高度普及的边缘场景中，缺乏中央控制器和预定的设备连接导致了复杂的网络结构，我们提出了一种通信高效的分散式联邦学习（DFL）算法来解决由数据和不同训练历史引起的异构学习难题，研究结果表明，与竞争方法相比，我们的解决方案能够训练出更好的本地模型并且在通信效率上更为优越。