Federated Learning (FL) presents a mechanism to allow decentralized training for machine learning (ML) models inherently enabling privacy preservation. The classical FL is implemented as a client-server system, which is known as Centralised Federated Learning (CFL). There are challenges inherent in CFL since all participants need to interact with a central server resulting in a potential communication bottleneck and a single point of failure. In addition, it is difficult to have a central server in some scenarios due to the implementation cost and complexity. This study aims to use Decentralised Federated learning (DFL) without a central server through one-hop neighbors. Such collaboration depends on the dynamics of communication networks, e.g., the topology of the network, the MAC protocol, and both large-scale and small-scale fading on links. In this paper, we employ stochastic geometry to model these dynamics explicitly, allowing us to quantify the performance of the DFL. The core objective is to achieve better classification without sacrificing privacy while accommodating for networking dynamics. In this paper, we are interested in how such topologies impact the performance of ML when deployed in practice. The proposed system is trained on a well-known MINST dataset for benchmarking, which contains labelled data samples of 60K images each with a size 28×28 pixels, and 1000 random samples of this MNIST dataset are assigned for each participant' device. The participants' devices implement a CNN model as a classifier model. To evaluate the performance of the model, a number of participants are randomly selected from the network. Due to randomness in the communication process, these participants interact with the random number of nodes in the neighborhood to exchange model parameters which are subsequently used to update the participants' individual models. These participants connected successfully with a varying number of neighbours to exchange parameters and update their global models. The results show that the classification prediction system can achieve 95% accuracy using the three different model optimizers in the training settings (i.e., SGD, ADAM, and RMSprop optimizers). Consequently, the DFL over mesh networking shows more flexibility in IoT systems, which reduces the communication cost and increases the convergence speed which can outperform CFL.INDEX TERMS Simplicity, privacy, federated learning, decentralization learning.
I. INTRODUCTIONI N recent years, the number of Internet of Things (IoT) and smart wearable devices have witnessed an increased proliferation in several vertical domains (e.g., wearables, home automation systems, smart glasses, health monitors, health-fitness trackers, smart grids, etc). These devices use a variety of wireless technologies and thus manifest different topological properties. For instance, LoRa deployment support one hop connection to the gateway with a distancedependent spreading factor manifesting star topology. In