分数规模的图神经网络
Graph Neural Networks at a Fraction
AI总结：
本文提出四元数消息传递神经网络（QMPNNs），以四分之一参数实现与原始GNN相当的性能，并重新定义图彩票票据以进一步压缩模型，在节点分类、链接预测和图分类任务上验证有效性。
摘要：
图神经网络（GNNs）已成为学习图结构数据表示的有力工具。除了实值GNN外，四元数GNN在图结构数据任务上也表现良好。为了减少能源足迹，我们在保持与原始规模GNN相当的精度的同时，减小模型尺寸。本文介绍了四元数消息传递神经网络（QMPNNs），这是一个利用四元数空间计算节点表示的框架。我们的方法提供了一种可泛化的方式，将四元数表示融入GNN架构，参数数量仅为原始的四分之一。此外，我们对图彩票票据提出了新的视角，重新定义了其在GNN和QMPNNs上下文中的适用性。我们特别旨在从GNN的子网络中找到初始化彩票，该彩票在训练后能达到与原始GNN相当的性能，从而进一步减少可训练模型参数。为了验证我们提出的QMPNN框架和LTH对GNN和QMPNNs的有效性，我们在三个基础图任务（节点分类、链接预测和图分类）的真实世界数据集上评估了它们的性能。
英文摘要：
Graph Neural Networks (GNNs) have emerged as powerful tools for learning representations of graph-structured data. In addition to real-valued GNNs, quaternion GNNs also perform well on tasks on graph-structured data. With the aim of reducing the energy footprint, we reduce the model size while maintaining accuracy comparable to that of the original-sized GNNs. This paper introduces Quaternion Message Passing Neural Networks (QMPNNs), a framework that leverages quaternion space to compute node representations. Our approach offers a generalizable method for incorporating quaternion representations into GNN architectures at one-fourth of the original parameter count. Furthermore, we present a novel perspective on Graph Lottery Tickets, redefining their applicability within the context of GNNs and QMPNNs. We specifically aim to find the initialization lottery from the subnetwork of the GNNs that can achieve comparable performance to the original GNN upon training. Thereby reducing the trainable model parameters even further. To validate the effectiveness of our proposed QMPNN framework and LTH for both GNNs and QMPNNs, we evaluate their performance on real-world datasets across three fundamental graph-based tasks: node classification, link prediction, and graph classification.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
