Extreme learning machineGraph convolutional networkSemi-supervised classificationEnsemble learningExtreme Learning Machine (ELM) has been widely used for various classification problems. However, the traditional ELMs are typically based on the regular Euclidean data, thus ignoring the intrinsic structured ...
基于图的半监督学习(Semi-Supervised Learning,SSL)是指基于少量标注数据和一个给定的指示所有数据之间连接关系的图结构来对未标注数据进行分类。最近,基于图的SSL由于其坚实的数学基础和令人满意的性能而受到越来越多的关注。 作为解决基于图的SSL问题的主流方法,图神经网络(Graph Neural Networks,GNN)近年来取得了令人...
3.1Graph-based semi-supervised learning SSL 方法专注于训练具有少量标记数据以及相对大量未标记数据的模型 。在过去的几十年中,基于图的 SSL 算法一直是最流行的研究课题之一。早期的基于图的技术是基于一个简单的假设设计的,即附近的节点可能具有相同的标签。这个目标可以通过拉普拉斯特征图、马尔可夫随机游走等的低维...
We consider an EM-like algorithm for semi-supervised learning on deep neural networks: In forward pass, the graph is constructed based on the network output, and the graph is then used for loss calculation to help update the network by back propagation in the backward pass. We demonstrate ...
A new semi-supervised learning framework is proposed by combing manifold regularization and data representation methods such as Non negative matrix factorization and sparse coding. We adopt unsupervised data representation methods as the learning machines because they do not depend on the labeled data, ...
文献阅读——Revisiting Semi-Supervised Learning with Graph Embeddings,程序员大本营,技术文章内容聚合第一站。
Virtual adversarial Semi-supervised learning Molecular property prediction Graph neural network 1. Introduction Deep learning has shown its great predictive power in the past few years and has been successfully applied to in the fields of bioinformatics and chemistry [1], [2], [3], [4], [5],...
论文信息 论文标题:Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning论文作者:Qimai Li, Zhichao Han, Xiao-Ming Wu论文来源:2018, AAAI论文地址:do
Semi-supervised learning with a graph-based approach has become increasingly popular in machine learning, particularly when dealing with situations where labeling data is a costly process. Graph Convolution Networks (GCNs) have been widely employed in semi-supervised learning, primarily on graph-structure...
Li Q., Han Z. and Wu X. Deeper insights into graph convolutional networks for semi-supervised learning. AAAI, 2018. 概 本文分析了 GCN 的实际上就是一种 Smoothing, 但是