This paper proposes a communication strategy for decentralized learning in wireless systems that employs adaptive modulation and coding capability. The main objective of this work is to address a critical issue in decentralized learning based on the cooperative stochastic gradient descent (C-SGD) over wireless systems: the relationship between the transmission rate and the network density influences the runtime performance of learning. We first present that a dense network topology does not necessarily benefit the iteration performance of learning than a sparse one. However, it tends to degrade the runtime performance because the dense network topology requires a low-rate transmission. Based on these findings, a communication strategy is proposed in which each node optimizes its transmission rate to minimize communication time during the C-SGD under the constraints of network density. We perform numerical simulations of an image classification task under both independent and identically distributed (i.i.d.) and non-i.i.d. settings. The simulation results reveal that the preferred setting for the network density depends on the channel conditions and the biases in the training samples. Furthermore, numerical simulations of an automatic modulation classification task indicate that the preferred setting is almost the same even if the training task is different.

中文翻译：

---

通过无线网络进行速率自适应的分散学习


本文提出了一种采用自适应调制和编码能力的无线系统中分散学习的通信策略。这项工作的主要目标是解决无线系统上基于协作随机梯度下降（C-SGD）的去中心化学习中的一个关键问题：传输速率和网络密度之间的关系影响学习的运行时性能。我们首先提出，密集的网络拓扑并不一定比稀疏的网络拓扑更有利于学习的迭代性能。然而，由于密集的网络拓扑需要低速率传输，因此它往往会降低运行时性能。基于这些发现，提出了一种通信策略，其中每个节点在网络密度的约束下优化其传输速率以最小化 C-SGD 期间的通信时间。我们在独立同分布 (iid) 和非独立同分布 (iid) 和非独立同分布 (iid) 设置下对图像分类任务进行数值模拟。仿真结果表明，网络密度的首选设置取决于信道条件和训练样本的偏差。此外，自动调制分类任务的数值模拟表明，即使训练任务不同，首选设置也几乎相同。