PKGCN: prior knowledge enhanced graph convolutional network for graph-based semi-supervised learning

2019 ◽  
Vol 10 (11) ◽  
pp. 3115-3127 ◽  
Author(s):  
Shaowei Yu ◽  
Xuebing Yang ◽  
Wensheng Zhang
Keyword(s):  
Supervised Learning ◽  
Prior Knowledge ◽  
Convolutional Network

scholarly journals Knowledge and Geo-Object Based Graph Convolutional Network for Remote Sensing Semantic Segmentation

Sensors ◽  
2021 ◽  
Vol 21 (11) ◽  
pp. 3848
Author(s):  
Wei Cui ◽  
Meng Yao ◽  
Yuanjie Hao ◽  
Ziwei Wang ◽  
Xin He ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Prior Knowledge ◽  
Contextual Information ◽  
Information Aggregation ◽  
Semantic Segmentation ◽  
Spatial Correlations ◽  
Convolutional Network ◽  
Object Based ◽  
Graph Neural Networks ◽  
Salt And Pepper

Pixel-based semantic segmentation models fail to effectively express geographic objects and their topological relationships. Therefore, in semantic segmentation of remote sensing images, these models fail to avoid salt-and-pepper effects and cannot achieve high accuracy either. To solve these problems, object-based models such as graph neural networks (GNNs) are considered. However, traditional GNNs directly use similarity or spatial correlations between nodes to aggregate nodes’ information, which rely too much on the contextual information of the sample. The contextual information of the sample is often distorted, which results in a reduction in the node classification accuracy. To solve this problem, a knowledge and geo-object-based graph convolutional network (KGGCN) is proposed. The KGGCN uses superpixel blocks as nodes of the graph network and combines prior knowledge with spatial correlations during information aggregation. By incorporating the prior knowledge obtained from all samples of the study area, the receptive field of the node is extended from its sample context to the study area. Thus, the distortion of the sample context is overcome effectively. Experiments demonstrate that our model is improved by 3.7% compared with the baseline model named Cluster GCN and 4.1% compared with U-Net.

Graph-Based Semi-Supervised Learning With Big Data

2020 ◽  
pp. 214-244
Author(s):  
Prithish Banerjee ◽  
Mark Vere Culp ◽  
Kenneth Jospeh Ryan ◽  
George Michailidis
Keyword(s):  
Machine Learning ◽  
Big Data ◽  
Supervised Learning ◽  
Prior Knowledge ◽  
Linear Algebra ◽  
Real Data ◽  
Data Set ◽  
Regression Problems ◽  
Classification And Regression ◽  
Empirical Demonstration

This chapter presents some popular graph-based semi-supervised approaches. These techniques apply to classification and regression problems and can be extended to big data problems using recently developed anchor graph enhancements. The background necessary for understanding this Chapter includes linear algebra and optimization. No prior knowledge in methods of machine learning is necessary. An empirical demonstration of the techniques for these methods is also provided on real data set benchmarks.

scholarly journals Semi-supervised segmentation and genome annotation

2020 ◽  
Author(s):  
Rachel C.W. Chan ◽  
Matthew McNeil ◽  
Eric G. Roberts ◽  
Mickaël Mendez ◽  
Maxwell W. Libbrecht ◽  
...  
Keyword(s):  
Supervised Learning ◽  
Prior Knowledge ◽  
Genome Annotation ◽  
Whole Genome ◽  
Transcription Start ◽  
Transcription Start Sites ◽  
Annotation Method ◽  
Supervised Segmentation ◽  
Unseen Data ◽  
Genome Annotations

AbstractSegmentation and genome annotation methods automatically discover joint signal patterns in whole genome datasets. Previously, researchers trained these algorithms in a fully unsupervised way, with no prior knowledge of the functions of particular regions. Adding information provided by expert-created annotations to supervise training could improve the annotations created by these methods. We implemented semi-supervised learning using virtual evidence in the annotation method Segway. Additionally, we defined a positionally tolerant precision and recall metric for scoring genome annotations based on the proximity of each annotation feature to the truth set. We demonstrate semi-supervised Segway’s ability to learn patterns corresponding to provided transcription start sites on a specified supervision label, and subsequently recover other transcription start sites in unseen data on the same supervision label.

Adaptive Graph Convolutional Network with Prior Knowledge for Action Recognition

2021 ◽  
pp. 597-607
Author(s):  
Guihong Lao ◽  
Lianyu Hu ◽  
Shenglan Liu ◽  
Zhuben Dong ◽  
Wujun Wen
Keyword(s):  
Prior Knowledge ◽  
Action Recognition ◽  
Convolutional Network

scholarly journals Multi-Stage Self-Supervised Learning for Graph Convolutional Networks on Graphs with Few Labeled Nodes

2020 ◽  
Vol 34 (04) ◽  
pp. 5892-5899
Author(s):  
Ke Sun ◽  
Zhouchen Lin ◽  
Zhanxing Zhu
Keyword(s):  
Supervised Learning ◽  
State Of The Art ◽  
Difficult Problem ◽  
Superior Performance ◽  
Learning Approach ◽  
Training Algorithm ◽  
Convolutional Network ◽  
Convolutional Networks ◽  
Learning Tasks ◽  
Multi Stage

Graph Convolutional Networks (GCNs) play a crucial role in graph learning tasks, however, learning graph embedding with few supervised signals is still a difficult problem. In this paper, we propose a novel training algorithm for Graph Convolutional Network, called Multi-Stage Self-Supervised (M3S) Training Algorithm, combined with self-supervised learning approach, focusing on improving the generalization performance of GCNs on graphs with few labeled nodes. Firstly, a Multi-Stage Training Framework is provided as the basis of M3S training method. Then we leverage DeepCluster technique, a popular form of self-supervised learning, and design corresponding aligning mechanism on the embedding space to refine the Multi-Stage Training Framework, resulting in M3S Training Algorithm. Finally, extensive experimental results verify the superior performance of our algorithm on graphs with few labeled nodes under different label rates compared with other state-of-the-art approaches.

scholarly journals Learning Non-Negativity Constrained Variation for Image Denoising and Deblurring

2017 ◽  
Vol 10 (4) ◽  
pp. 852-871 ◽  
Author(s):  
Tengda Wei ◽  
Linshan Wang ◽  
Ping Lin ◽  
Jialing Chen ◽  
Yangfan Wang ◽  
...  
Keyword(s):  
Supervised Learning ◽  
Prior Knowledge ◽  
Image Denoising ◽  
Learning Strategy ◽  
Experimental Results ◽  
Variational Model ◽  
Training Samples ◽  
Heuristic Learning ◽  
Constrained Variation ◽  
Constraint Method

AbstractThis paper presents a heuristic Learning-based Non-Negativity Constrained Variation (L-NNCV) aiming to search the coefficients of variational model automatically and make the variation adapt different images and problems by supervised-learning strategy. The model includes two terms: a problem-based term that is derived from the prior knowledge, and an image-driven regularization which is learned by some training samples. The model can be solved by classicalε-constraint method. Experimental results show that: the experimental effectiveness of each term in the regularization accords with the corresponding theoretical proof; the proposed method outperforms other PDE-based methods on image denoising and deblurring.

Ensemble Based Graph Convolutional Network for Semi Supervised Learning

2021 ◽  
pp. 443-451
Author(s):  
Rakesh Kumar Yadav ◽  
Manikanta Moghili ◽  
Abhishek ◽  
Prashant Shukla ◽  
Shekhar Verma
Keyword(s):  
Supervised Learning ◽  
Convolutional Network

scholarly journals Co-GCN for Multi-View Semi-Supervised Learning

2020 ◽  
Vol 34 (04) ◽  
pp. 4691-4698
Author(s):  
Shu Li ◽  
Wen-Tao Li ◽  
Wei Wang
Keyword(s):  
Supervised Learning ◽  
Real World ◽  
State Of The Art ◽  
Data Sets ◽  
Real World Data ◽  
Convolutional Network ◽  
The Past ◽  
Real World Applications ◽  
Supervised Methods ◽  
Disjoint Sets

In many real-world applications, the data have several disjoint sets of features and each set is called as a view. Researchers have developed many multi-view learning methods in the past decade. In this paper, we bring Graph Convolutional Network (GCN) into multi-view learning and propose a novel multi-view semi-supervised learning method Co-GCN by adaptively exploiting the graph information from the multiple views with combined Laplacians. Experimental results on real-world data sets verify that Co-GCN can achieve better performance compared with state-of-the-art multi-view semi-supervised methods.

Sign in / Sign up

Export Citation Format

Share Document