paper-with-me

홈 › Papers

Dual Graph Convolutional Networks for Graph-Based Semi-Supervised Classification

2018-04-01 · World Wide Web Conference 2018 4 · Chengyi Zhuang, Qiang Ma

The problem of extracting meaningful data through graph analysis spans a range of different fields, such as the internet, social networks, biological networks, and many others. The importance of being able to effectively mine and learn from such data continues to grow as more and more structured data become available. In this paper, we present a simple and scalable semi-supervised learning method for graph-structured data in which only a very small portion of the training data are labeled. To sufficiently embed the graph knowledge, our method performs graph convolution from different views of the raw data. In particular, a dual graph convolutional neural network method is devised to jointly consider the two essential assumptions of semi-supervised learning: (1) local consistency and (2) global consistency. Accordingly, two convolutional neural networks are devised to embed the local-consistency-based and global-consistency-based knowledge, respectively. Given the different data transformations from the two networks, we then introduce an unsupervised temporal loss function for the ensemble. In experiments using both unsupervised and supervised loss functions, our method outperforms state-of-the-art techniques on different datasets.

📄 PDF Abstract BibTeX

Code (2)

code-implementation1/Code9/tree/main/dgcn mindspore
mindspore-ai/models/blob/master/research/gnn/dgcn mindspore

Tasks

Classification

Similar Papers 제목 키워드 기반

TWIN GRAPH CONVOLUTIONAL NETWORKS: GCN WITH DUAL GRAPH SUPPORT FOR SEMI-SUPERVISED LEARNING

2019-09-25 · Feng Shi, Yizhou Zhao, Ziheng Xu, Tianyang Liu 외

Graph Neural Networks as a combination of Graph Signal Processing and Deep Convolutional Networks shows great power in pattern recognition in non-Euclidean domains. In this paper, we propose a new method to deploy two pi…

Graph Convolutional Network For Semi-supervised Node Classification With Subgraph Sketching

2024-04-19 · Zibin Huang, Jun Xian

In this paper, we propose the Graph-Learning-Dual Graph Convolutional Neural Network called GLDGCN based on the classic Graph Convolutional Neural Network(GCN) by introducing dual convolutional layer and graph learning l…

ClassificationClusteringGraph LearningNode Classification

Semi-Supervised Learning With Graph Learning-Convolutional Networks

2019-06-01 · CVPR 2019 6 · Bo Jiang, Ziyan Zhang, Doudou Lin, Jin Tang 외

Graph Convolutional Neural Networks (graph CNNs) have been widely used for graph data representation and semi-supervised learning tasks. However, existing graph CNNs generally use a fixed graph which may not be optimal f…

graph constructionGraph Learning

Fully Linear Graph Convolutional Networks for Semi-Supervised Learning and Clustering

2021-11-15 · Yaoming Cai, Zijia Zhang, Zhihua Cai, Xiaobo Liu 외

This paper presents FLGC, a simple yet effective fully linear graph convolutional network for semi-supervised and unsupervised learning. Instead of using gradient descent, we train FLGC based on computing a global optima…

ClusteringComputational Efficiency

Graph Learning-Convolutional Networks

2018-11-25 · Bo Jiang, Ziyan Zhang, Doudou Lin, Jin Tang

Recently, graph Convolutional Neural Networks (graph CNNs) have been widely used for graph data representation and semi-supervised learning tasks. However, existing graph CNNs generally use a fixed graph which may be not…

graph constructionGraph Learning