p2pGNN：用于点对点网络中节点分类的分散图神经网络

在这项工作中，我们旨在对具有通信不确定性的非结构化点对点网络的节点进行分类，例如去中心化的社交网络的用户。众所周知，图神经网络（GNN）通过利用自然发生的网络链接来提高集中式环境中较简单的分类器的准确性，但当节点邻居不是经常可用时，图卷积层在分散式环境中的实现是具有挑战性的。我们通过采用解耦的GNN来解决这个问题，其中基础分类器的预测和错误在训练后通过图形扩散。对于这些，我们部署了预先训练好的和流言训练好的基础分类器，并在通信不确定的情况下实现了点对点的图形扩散。特别是，我们开发了一个异步分散的扩散公式，该公式在相同的预测下线性地收敛于通信速率。我们在三个具有节点特征和标签的真实世界图上进行了实验，并模拟了具有均匀随机通信频率的点对点网络；给定一部分已知标签，我们的分散图扩散实现了与集中式GNN相当的准确性。

原文题目：p2pGNN: A Decentralized Graph Neural Network for Node Classification in Peer-to-Peer Networks

原文：In this work, we aim to classify nodes of unstructured peer-to-peer networks with communication uncertainty, such as users of decentralized social networks. Graph Neural Networks (GNNs) are known to improve the accuracy of simpler classifiers in centralized settings by leveraging naturally occurring network links, but graph convolutional layers are challenging to implement in decentralized settings when node neighbors are not constantly available. We address this problem by employing decoupled GNNs, where base classifier predictions and errors are diffused through graphs after training. For these, we deploy pre-trained and gossip-trained base classifiers and implement peer-to-peer graph diffusion under communication uncertainty. In particular, we develop an asynchronous decentralized formulation of diffusion that converges at the same predictions linearly with respect to communication rate. We experiment on three real-world graphs with node features and labels and simulate peer-to-peer networks with uniformly random communication frequencies; given a portion of known labels, our decentralized graph diffusion achieves comparable accuracy to centralized GNNs.