NodeNet：一种用于节点分类的图正则化神经网络
NodeNet: A Graph Regularised Neural Network for Node Classification
摘要：
真实世界的事件表现出高度的相互依存和联系，因此产生的数据点也继承了这种联系。然而，大多数AI/ML技术忽略了数据点之间的联系。最近对基于图的AI/ML技术的兴趣激增旨在利用这些联系。基于图的学习算法有效地利用数据和相关信息来构建更好的模型。神经图学习（NGL）是一种这样的技术，其利用具有修改的损失函数的传统机器学习算法来利用图结构中的边。在本文中，我们提出了一个模型，使用NGL -节点网，解决节点分类任务的引文图。我们讨论我们的修改和它们与任务的相关性。我们进一步将我们的结果与当前最先进的技术进行比较，并调查NodeNet卓越性能的原因。
英文摘要：
Real-world events exhibit a high degree of interdependence and connections, and hence data points generated also inherit the linkages. However, the majority of AI/ML techniques leave out the linkages among data points. The recent surge of interest in graph-based AI/ML techniques is aimed to leverage the linkages. Graph-based learning algorithms utilize the data and related information effectively to build superior models. Neural Graph Learning (NGL) is one such technique that utilizes a traditional machine learning algorithm with a modified loss function to leverage the edges in the graph structure. In this paper, we propose a model using NGL - NodeNet, to solve node classification task for citation graphs. We discuss our modifications and their relevance to the task. We further compare our results with the current state of the art and investigate reasons for the superior performance of NodeNet.
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。
