23,235 Hits in 4.8 sec

Structured Graph Learning for Clustering and Semi-supervised Classification [article]

Zhao Kang and Chong Peng and Qiang Cheng and Xinwang Liu and Xi Peng and Zenglin Xu and Ling Tian
2020 arXiv   pre-print
Furthermore, most existing graph-based methods conduct clustering and semi-supervised classification on the graph learned from the original data matrix, which doesn't have explicit cluster structure, thus  ...  Graph-based clustering and semi-supervised classification techniques have shown impressive performance.  ...  In essence, both clustering and semi-supervised classification algorithms are trying to predict labels for samples [9] .  ... 
arXiv:2008.13429v1 fatcat:zrgfgv56cngl3kovmdodte3e4a

Collaborative Graph Convolutional Networks: Unsupervised Learning Meets Semi-Supervised Learning

Binyuan Hui, Pengfei Zhu, Qinghua Hu
Graph convolutional networks (GCN) have achieved promising performance in attributed graph clustering and semi-supervised node classification because it is capable of modeling complex graphical structure  ...  CGCN is composed of an attributed graph clustering network and a semi-supervised node classification network.  ...  Acknowledgments This work was supported by the National Natural Science Foundation of China under Grants 61876127, Natural Science Foundation of Tianjin Under Grants 17JCZDJC30800, 18YFZCGX00390, 18YFZCGX00680, and  ... 
doi:10.1609/aaai.v34i04.5843 fatcat:6nsxdrutsngubko4ii5qpgk6vu

Regularized Semi-supervised Classification on Manifold [chapter]

Lianwei Zhao, Siwei Luo, Yanchang Zhao, Lingzhi Liao, Zhihai Wang
2006 Lecture Notes in Computer Science  
In this paper, we focus on a regularization approach for semi-supervised classification.  ...  Then we propose a novel regularized semi-supervised classification algorithm, in which the regularization term is based on the modified Graph Laplacian.  ...  The research is supported by the National Natural Science Foundations of China (60373029) and the National Research Foundation for the Doctoral Program of Higher Education of China (20050004001).  ... 
doi:10.1007/11731139_5 fatcat:mznpx3gglnektm7vbdgpiqqcy4

Synthetic Graph Generation to Benchmark Graph Learning [article]

Anton Tsitsulin, Benedek Rozemberczki, John Palowitch, Bryan Perozzi
2022 arXiv   pre-print
Graph learning algorithms have attained state-of-the-art performance on many graph analysis tasks such as node classification, link prediction, and clustering.  ...  In the case study, we show how our framework provides insight into unsupervised and supervised graph neural network models.  ...  We verify that our framework delivers actionable scientific insights on two case studies for unsupervised and supervised graph learning models.  ... 
arXiv:2204.01376v1 fatcat:fwjn5yrqkveljfgq6ep3tjkebm

Semi-supervised classification learning by discrimination-aware manifold regularization

Yunyun Wang, Songcan Chen, Hui Xue, Zhenyong Fu
2015 Neurocomputing  
Manifold regularization (MR) provides a powerful framework for semi-supervised classification (SSC) using both the labeled and unlabeled data.  ...  It first constructs a single Laplacian graph over the whole dataset for representing the manifold structure, and then enforces the smoothness constraint over such graph by a Laplacian regularizer in learning  ...  MR for semi-supervised classification represents the manifold structure for the whole dataset by a single Laplacian graph, which is different from MR for supervised classification constructing the respective  ... 
doi:10.1016/j.neucom.2014.06.059 fatcat:cpus3yescrbwdetzvurjbahg7y

Semi-supervised learning: a brief review

Y C A Padmanabha Reddy, P Viswanath, B Eswara Reddy
2018 International Journal of Engineering & Technology  
Traditionally SSL is classified in to Semi-supervised Classification and Semi-supervised Clustering which achieves better accuracy than traditional supervised and unsupervised learning techniques.  ...  Semi-supervised learning addresses this problem and act as a half way between supervised and unsupervised learning.  ...  Semi-supervised learning is further dived into two types i) Semi-Supervised classification and ii) Semi-Supervised Clustering is discussed in the below section.  ... 
doi:10.14419/ijet.v7i1.8.9977 fatcat:qex5q57idzcsdlyhjnsw4zvbwq

Multi-task Self-distillation for Graph-based Semi-Supervised Learning [article]

Yating Ren and Junzhong Ji and Lingfeng Niu and Minglong Lei
2022 arXiv   pre-print
Graph convolutional networks have made great progress in graph-based semi-supervised learning.  ...  In this paper, we propose a multi-task self-distillation framework that injects self-supervised learning and self-distillation into graph convolutional networks to separately address the mismatch problem  ...  Introduction Semi-supervised learning on graphs (GSSL) is a fundamental machine learning task with only limited labels for graph nodes available.  ... 
arXiv:2112.01174v3 fatcat:24qnhmc2abasbmwr6chx46ctae

Hybrid Graph Convolutional Network for Semi-supervised Retinal Image Classification

Guanghua Zhang, Jing Pan, Zhaoxia Zhang, Heng Zhang, Changyuan Xing, Bin Sun, Ming Li
2021 IEEE Access  
INDEX TERMS Retinal image classification, semi-supervised, graph convolutional network, modularitybased graph learning.  ...  Hence we proposes a semi-supervised retinal image classification method by a Hybrid Graph Convolutional Network (HGCN).  ...  This network learns the synthetic structural information in semi-supervised VOLUME 9, 2021 learning, and the experimental results show the effectiveness of HGCN on semi-supervised retinal image classification  ... 
doi:10.1109/access.2021.3061690 fatcat:mod2mr3kt5a6fn5iwguocplnjq

A structural cluster kernel for learning on graphs

Madeleine Seeland, Andreas Karwath, Stefan Kramer
2012 Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining - KDD '12  
We applied our novel kernel in a supervised and a semi-supervised setting to regression and classification problems on a number of real-world datasets of molecular graphs.  ...  In recent years, graph kernels have received considerable interest within the machine learning and data mining community.  ...  In work by Bodo and Csato [3] a kernel construction algorithm for supervised and semi-supervised learning was proposed, which constitutes a general framework for semi-supervised kernel construction.  ... 
doi:10.1145/2339530.2339614 dblp:conf/kdd/SeelandKK12 fatcat:maalh6bjcnb6jealz7d2np5lei

Graph Construction with Label Information for Semi-Supervised Learning [article]

Liansheng Zhuang, Zihan Zhou, Jingwen Yin, Shenghua Gao, Zhouchen Lin, Yi Ma, Nenghai Yu
2017 arXiv   pre-print
for semi-supervised learning tasks.  ...  such as the Low-Rank Representation (LRR), and propose a novel semi-supervised graph learning method called Semi-Supervised Low-Rank Representation (SSLRR).  ...  To apply the semi-supervised graph learning methods, we randomly select and label 30% of the observed samples from each cluster.  ... 
arXiv:1607.02539v3 fatcat:va6eqworsfeidagiarl4nyouhi

Learning With $\ell ^{1}$-Graph for Image Analysis

Bin Cheng, Jianchao Yang, Shuicheng Yan, Yun Fu, T.S. Huang
2010 IEEE Transactions on Image Processing  
Extensive experiments on three real-world datasets show the consistent superiority of 1 -graph over those classic graphs in data clustering, subspace learning, and semi-supervised learning tasks.  ...  Then, a series of new algorithms for various machine learning tasks, e.g., data clustering, subspace learning, and semisupervised learning, are derived upon the 1 -graphs.  ...  Learning With`1-Graph for Image Analysis of Gaussian random field over the graph for semi-supervised learning.  ... 
doi:10.1109/tip.2009.2038764 pmid:20031500 fatcat:lbju2dvonvb2hijji55ueqme6a

Hyperspectral Image Classification Through Bilayer Graph-Based Learning

Yue Gao, Rongrong Ji, Peng Cui, Qionghai Dai, Gang Hua
2014 IEEE Transactions on Image Processing  
For graph-based classification, how to establish the neighboring relationship among the pixels from the high dimensional features is the key toward a successful classification.  ...  Our graph learning algorithm contains two layers. The first-layer constructs a simple graph, where each vertex denotes one pixel and the edge weight encodes the similarity between two pixels.  ...  For instance, the neighborhood relationships among all pixels are modeled by a graph structure in [16] , and a semi-supervised learning procedure is conducted for hyperspectral image classification.  ... 
doi:10.1109/tip.2014.2319735 pmid:24771580 fatcat:6knm6gexiffl7drrh2b7xjzmey

Modularity Optimization as a Training Criterion for Graph Neural Networks [chapter]

Tsuyoshi Murata, Naveed Afzal
2018 Complex Networks IX  
Graph convolution is a recent scalable method for performing deep feature learning on attributed graphs by aggregating local node information over multiple layers.  ...  Experimental evaluation on two attributed bibilographic networks showed that the incorporation of the community-preserving objective improves semi-supervised node classification accuracy in the sparse  ...  Acknowledgement This work was supported by Tokyo Tech -Fuji Xerox Cooperative Research (Project Code KY260195), JSPS Grant-in-Aid for Scientific Research(B) (Grant Number 17H01785) and JST CREST (Grant  ... 
doi:10.1007/978-3-319-73198-8_11 fatcat:avi7smb6xjcrbeetpusgmplmxq

Shoestring: Graph-Based Semi-Supervised Learning with Severely Limited Labeled Data [article]

Wanyu Lin, Zhaolin Gao, Baochun Li
2020 arXiv   pre-print
Graph-based semi-supervised learning has been shown to be one of the most effective approaches for classification tasks from a wide range of domains, such as image classification and text classification  ...  More specifically, we address the problem of graph-based semi-supervised learning in the presence of severely limited labeled samples, and propose a new framework, called Shoestring, that improves the  ...  Revisiting Graph-based Semi-Supervised Learning We do not attempt to provide a comprehensive literature review on graph-based semi-supervised learning.  ... 
arXiv:1910.12976v2 fatcat:bc2uikyhgnb6hifwzdw2m6psny

Semi-Supervised Deep Learning for Multiplex Networks [article]

Anasua Mitra, Priyesh Vijayan, Ranbir Sanasam, Diganta Goswami, Srinivasan Parthasarathy, Balaraman Ravindran
2021 arXiv   pre-print
In this work, we present a novel semi-supervised approach for structure-aware representation learning on multiplex networks.  ...  Our approach relies on maximizing the mutual information between local node-wise patch representations and label correlated structure-aware global graph representations to model the nodes and cluster structures  ...  In particular, for the semi-supervised classification task, we define label-correlated structure-aware clusters that jointly learn node and cluster representations by optimizing the InfoMax principle.  ... 
arXiv:2110.02038v1 fatcat:koof45ms6fbrpaz6izecoswroi
« Previous Showing results 1 — 15 out of 23,235 results