论文阅读 [TPAMI-2022] On Inductive–Transductive Learning With Graph Neural Networks

论文阅读 [TPAMI-2022] On Inductive–Transductive Learning With Graph Neural Networks

论文搜索(studyai.com)

搜索论文: On Inductive–Transductive Learning With Graph Neural Networks

搜索论文: http://www.studyai.com/search/whole-site/?q=On+Inductive–Transductive+Learning+With+Graph+Neural+Networks

关键字(Keywords)

Neural networks; Computational modeling; Training; Encoding; Graph neural networks; Topology; Diffusion processes; Graph neural networks; transductive learning; inductive learning

机器学习

监督学习; 图网络; 图卷积网络

摘要(Abstract)

Many real–world domains involve information naturally represented by graphs, where nodes denote basic patterns while edges stand for relationships among them.

许多现实世界中的域都包含由图形自然表示的信息，其中节点表示基本模式，边表示它们之间的关系。.

The graph neural network (GNN) is a machine learning model capable of directly managing graph–structured data.

图形神经网络（GNN）是一种能够直接管理图形结构数据的机器学习模型。.

In the original framework, GNNs are inductively trained, adapting their parameters based on a supervised learning environment.

在最初的框架中，GNN经过归纳训练，根据有监督的学习环境调整参数。.

However, GNNs can also take advantage of transductive learning, thanks to the natural way they make information flow and spread across the graph, using relationships among patterns.

然而，GNN也可以利用转换学习，这要归功于它们利用模式之间的关系使信息在图形中流动和传播的自然方式。.

In this paper, we propose a mixed inductive–transductive GNN model, study its properties and introduce an experimental strategy that allows us to understand and distinguish the role of inductive and transductive learning.

在本文中，我们提出了一个混合的归纳-转导GNN模型，研究了它的性质，并介绍了一种实验策略，使我们能够理解和区分归纳学习和转导学习的作用。.

The preliminary experimental results show interesting properties for the mixed model, highlighting how the peculiarities of the problems and the data can impact on the two learning strategies…

初步实验结果显示了混合模型的有趣特性，突出了问题和数据的特殊性如何影响这两种学习策略。。.

作者(Authors)

[‘Giorgio Ciano’, ‘Alberto Rossi’, ‘Monica Bianchini’, ‘Franco Scarselli’]