检索结果-内蒙古大学图书馆

Pseudo Contrastive learning for graph-based semi-supervised learning

NEUROCOMPUTING 2025年 624卷

作者： Lu, Weigang Guan, Ziyu Zhao, Wei Yang, Yaming Lv, Yuanhai Xing, Lining Yu, Baosheng Tao, Dacheng Xidian Univ Sch Comp Sci & Technol Xian Peoples R China Northwest Univ Xian Univ Posts & Telecommun Sch Informat Sci & Technol Xian Peoples R China Xian Univ Posts & Telecommun Informat Network Ctr Xian Peoples R China Xidian Univ Sch Elect Engn Xian Peoples R China Univ Sydney Sydney Australia Nanyang Technol Univ Nanyang Singapore

Pseudo Labeling is a technique used to improve the performance of semi-supervised graph Neural Networks (GNNs) by generating additional pseudo-labels based on confident predictions. However, the quality of generated pseudo-labels has been a longstanding concern due to the sensitivity of the classification objective with respect to the given labels. To avoid the untrustworthy classification supervision indicating "anode belongs to a specific class", we favor the fault-tolerant contrasting supervision demonstrating "two nodes do not belong to the same class". Thus, the problem of generating high-quality pseudo-labels is then transformed into a relaxed version, i.e ., identifying reliable negative pairs. To achieve this, we propose a general framework for GNNs, termed Pseudo Contrastive learning (PCL). It separates two nodes whose positive and negative pseudo- labels target the same class. To incorporate topological knowledge into learning, we devise a topologically weighted contrastive loss that spends more effort separating negative pairs with smaller topological distances. Experimentally, we apply PCL to various GNNs, which consistently outperform their counterparts using other popular general techniques on five real-world graphs.

关键词： Contrastive learning Pseudo Labeling Node classification graph-based semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

graph-based semi-supervised learning with non-convex graph total variation regularization

引用

EXPERT SYSTEMS WITH APPLICATIONS 2024年第PartC期225卷

作者： Wen, Tiehong Chen, Zhong Zhang, Tao Zou, Jian Yangtze Univ Sch Informat & Math Jingzhou 434023 Hubei Peoples R China

graph total variation (GTV) is a widely employed regularization in graph-based semi-supervised learning (GSSL), which enforce the piece-wise smoothness of the label values concerning the underlying graph structure. However, due to its inherently biased estimation, GTV regularization tends to cause an underestimation of label values on boundary nodes . In this paper, we propose a novel GSSL model with non-convex GTV regularization. Specifically, we construct the non-convex GTV regularization by subtracting the generalized Moreau envelope from the original GTV regularization term, which can reduce the estimation bias and thus effectively estimate the label values of the boundary nodes. We demonstrate that under certain conditions of the non-convex control parameter, our proposed GSSL model maintains global convexity, thereby providing a theoretical guarantee for algorithm convergence. Additionally, we present an efficient alternating direction multiplier method (ADMM) to solve the proposed model. Finally, we validate the effectiveness on both synthetic data and background subtraction. The proposed GSSL model outperforms state-of-the-art model with a 17.97% improvement in SNR value on synthetic data, and increases average recall, average precision, and average F-measure by 4.92%, 1.19%, and 1.57% respectively on the pan-tilt-zoom(PTZ) challenge of background subtraction.

关键词： graph-based semi-supervised learning graph total variation regularization Non-convex regularization Background subtraction

来源：评论

学校读者我要写书评

暂无评论

An Effective Induction Motor Fault Diagnosis Approach Using graph-based semi-supervised learning

引用

IEEE ACCESS 2021年 9卷 7471-7482页

作者： Zaman, Shafi Md Kawsar Liang, Xiaodong Mem Univ Newfoundland Dept Elect & Comp Engn St John NF A1B 3X5 Canada Univ Saskatchewan Dept Elect & Comp Engn Saskatoon SK S7N 5A9 Canada

Machine learning has paved its way into induction motors fault diagnosis area, where supervised learning and deep learning have been employed. However, both learning methods require a large amount of labeled data to train the model, which pose significant challenges in real life applications. To overcome this issue, in this paper, the graph-based semi-supervised learning (GSSL) is adopted to develop a fault diagnosis method for direct online induction motors due to GSSL's superior feature that only a small amount of labeled data is needed in training datasets. To evaluate its suitability, the greedy-gradient max cut (GGMC) algorithm in the GSSL family is chosen in this study, and an effective fault diagnosis approach is developed using experimental stator currents recorded in the lab for two induction motors. The developed approach can conduct binary and multiclass classifications for faults on direct online induction motors. As a critical step, curve fitting equations are developed to calculate features for untested motor loadings by using experimental data for tested motor loadings, which enables the proposed approach to remain effective under all potential motor loading conditions.

关键词： Discrete wavelet transform fault diagnosis graph-based semi-supervised learning greedy-gradient max cut induction motors stator current

来源：评论

学校读者我要写书评

暂无评论

Noise-robust graph-based semi-supervised learning with dynamic shaving label propagation

引用

APPLIED SOFT COMPUTING 2023年 142卷

作者： Lee, Jiyoon Kim, Younghoon Kim, Seoung Bum Korea Univ Sch Ind Management Engn 145 Anam Ro Seoul 02841 South Korea Kyung Hee Univ Dept Ind & Management Syst Engn 1732 Deogyeong Daero Yongin 17104 Gyeonggi South Korea

graph-based semi-supervised classification is widely used because it effectively exploits the characteristics of unlabeled data. However, the existing methods have a drawback in that they do not account for the inherent noise of the data. Noise in graph data refers to nodes that are isolated from classes and overlapping nodes between different classes. Therefore, neglecting noise can distort the data manifold, leading to over-smoothing and overall performance degradation. In this paper, we propose a noiserobust model called the dynamic shaving label propagation algorithm. Our proposed method comprises three parts: graph construction, noise definition and cutting, and label propagation. First, in the graph construction process, k is determined at the point when reverse nearest neighbors are identified for the most isolated nodes. Second, the noise definition process identifies the nodes classified as noise based on the number and distance of their reverse nearest neighbors. Finally, label propagation is performed dynamically and iteratively by adjusting the noise removal intensity. Using various simulated and realworld datasets, we evaluate the accuracy and noise robustness of the proposed method with those of existing methods to evaluate its effectiveness and applicability. The comparison results demonstrate that the proposed method outperforms the existing alternatives. & COPY;2023 Elsevier B.V. All rights reserved.

关键词： graph-based semi-supervised learning Label propagation Noise shaving Node cutting Pseudo-density noise detection

来源：评论

学校读者我要写书评

暂无评论

FuzzyGSSL: An Improved graph-based semi-supervised learning Through Fuzzy Label Propagation 24

FuzzyGSSL: An Improved Graph-based Semi-Supervised Learning ...

引用

Proceedings of the 3rd International Conference on Computing Advancements

作者： Kaniz Fatema Tanni Tanjila Sarkar Promi M. Jamshed Alam Patwary International Islamic University Chittagong Chittagong Bangladesh International Islamic University Chittagong Chittagong Chittagong Bangladesh Chittagong University of Engineering & Technology Chittagong Bangladesh

来源：评论

学校读者我要写书评

暂无评论

A simple graph-based semi-supervised learning approach for imbalanced classification

引用

PATTERN RECOGNITION 2021年 118卷 108026-108026页

作者： Deng, Jianjin Yu, Jin-Gang Univ Texas Arlington Dept Comp Sci & Engn 500 UTA Blvd Arlington TX 76010 USA South China Univ Technol Sch Automat Sci & Technol Guangzhou 510641 Peoples R China Pazhou Lab Guangzhou 510335 Peoples R China

graph-based semi-supervised learning (GSSL) methods aim to classify unlabeled data by learning the graph structure and labeled data jointly. In this work, we propose a simple GSSL approach, which can deal with various degrees of class imbalance in given datasets. The key idea is to estimate the class proportion of input data in order to enhance the discriminative power of learned smooth classification function on the graph. Moreover, it has interesting connections to the regularization framework, the Markov stability for graph partition and the group inverse of normalized Laplacain matrix. For classification problems, experimental results demonstrate our approach can achieve promising performance on several datasets with varying class imbalance. (c) 2021 Elsevier Ltd. All rights reserved.

关键词： graph-based semi-supervised learning Class imbalance Markov stability Group inverse

来源：评论

学校读者我要写书评

暂无评论

Aspect Term Extraction using graph-based semi-supervised learning

Aspect Term Extraction using Graph-based Semi-Supervised Lea...

引用

International Conference on Computational Intelligence and Data Science (ICCIDS)

作者： Ansari, Gunjan Saxena, Chandni Ahmad, Tanvir Doja, M. N. JSS Acad Tech Educ Sec 62 Noida Uttar Pradesh India Jamia Millia Islamia Dept Comp Engn New Delhi 25 India

Aspect based Sentiment Analysis is a major subarea of sentiment analysis. Many supervised and unsupervised approaches have been proposed in the past for detecting and analyzing the sentiment of aspect terms. In this paper, a graph-based semi-supervised learning approach for aspect term extraction is proposed. In this approach, every identified token in the review document is classified as aspect or non-aspect term from a small set of labeled tokens using label spreading algorithm. The k-Nearest Neighbor (kNN) for graph sparsification is employed in the proposed approach to make it more time and memory efficient. The proposed work is further extended to determine the polarity of the opinion words associated with the identified aspect terms in review sentence to generate visual aspect-based summary of review documents. The experimental study is conducted on benchmark and crawled datasets of restaurant and laptop domains with varying value of labeled instances. The results depict that the proposed approach could achieve good result in terms of Precision, Recall and Accuracy with limited availability of labeled data. (C) 2020 The Authors. Published by Elsevier B.V.

关键词： Aspect based sentiment analysis graph-based semi-supervised learning opinion summary label spreading

来源：评论

学校读者我要写书评

暂无评论

Aspect Term Extraction using graph-based semi-supervised learning

引用

Procedia Computer Science 2020年 167卷 2080-2090页

作者： Gunjan Ansari Chandni Saxena Tanvir Ahmad M.N. Doja J.S.S. Academy of Technical Education Sec-62 Noida Uttar Pradesh India Department of Computer Engineering Jamia Millia Islamia New Delhi-25 India

关键词： Aspect based sentiment analysis graph-based semi-supervised learning opinion summary label spreading

来源：评论

学校读者我要写书评

暂无评论

Instance selection method for improving graph-based semi-supervised learning

引用

Frontiers of Computer Science 2018年第4期12卷 725-735页

作者： Hai WANG Shao-Bo WANG Yu-Feng LI 1 National Key Laboratory for Novel Software Technology Nanjing University Nanjing 210023 China Collaborative Innovation Center of Novel Software Technology and Industrialization Nanjing 210023 China

graph-based semi-supervised learning is an important semi-supervised learning paradigm. Although graphbased semi-supervised learning methods have been shown to be helpful in various situations, they may adversely affect performance when using unlabeled data. In this paper, we propose a new graph-based semi-supervised learning method based on instance selection in order to reduce the chances of performance degeneration. Our basic idea is that given a set of unlabeled instances, it is not the best approach to exploit all the unlabeled instances; instead, we should exploit the unlabeled instances that are highly likely to help improve the performance, while not taking into account the ones with high risk. We develop both transductive and inductive variants of our method. Experiments on a broad range of data sets show that the chances of performance degeneration of our proposed method are much smaller than those of many state-of-the-art graph-based semi-supervised learning methods.

关键词： graph-based semi-supervised learning performance degeneration instance selection

来源：评论

学校读者我要写书评

暂无评论

Visual Texture Perception via graph-based semi-supervised learning 9

Visual Texture Perception via Graph-based Semi-supervised Le...

引用

9th International Conference on graphic and Image Processing (ICGIP)

作者： Zhang, Qin Dong, Junyu Zhong, Guoqiang Ocean Univ China Dept Comp & Technol Qingdao Peoples R China

ISBN: (数字)9781510617421

ISBN: (纸本)9781510617421

Perceptual features, for example direction, contrast and repetitiveness, are important visual factors for human to perceive a texture. However, it needs to perform psychophysical experiment to quantify these perceptual features' scale, which requires a large amount of human labor and time. This paper focuses on the task of obtaining perceptual features' scale of textures by small number of textures with perceptual scales through a rating psychophysical experiment (what we call labeled textures) and a mass of unlabeled textures. This is the scenario that the semi-supervised learning is naturally suitable for. This is meaningful for texture perception research, and really helpful for the perceptual texture database expansion. A graph-based semi-supervised learning method called random multi-graphs, RMG for short, is proposed to deal with this task. We evaluate different kinds of features including LBP, Gabor, and a kind of unsupervised deep features extracted by a PCA-based deep network. The experimental results show that our method can achieve satisfactory effects no matter what kind of texture features are used.

关键词： Texture perception graph-based semi-supervised learning random multi-graphs

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：