论文标题
NodeNet：用于节点分类的图形正规化神经网络
NodeNet: A Graph Regularised Neural Network for Node Classification
论文作者
论文摘要
现实世界中的事件表现出高度的相互依赖性和连接，因此生成的数据点也继承了链接。但是，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链接。基于图的学习算法利用数据和相关信息有效地构建了出色的模型。神经图学习（NGL）就是这样一种技术，它利用具有修改后的损耗函数的传统机器学习算法来利用图形结构中的边缘。在本文中，我们提出了一个使用NGL -NodeNet的模型，以求解引用图的节点分类任务。我们讨论我们的修改及其与任务的相关性。我们进一步将结果与当前的最新状态进行了比较，并研究了NodeNet出色表现的原因。
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.
