Semi-supervised Classification Method Research Articles

GraphHop: An Enhanced Label Propagation Method for Node Classification.

A scalable semisupervised node classification method on graph-structured data, called GraphHop, is proposed in this work. The graph contains all nodes' attributes and link connections but labels of only a subset of nodes. Graph convolutional networks (GCNs) have provided superior performance in node label classification over the traditional label propagation (LP) methods for this problem. Nevertheless, current GCN algorithms suffer from a considerable amount of labels for training because of high model complexity or cannot be easily generalized to large-scale graphs due to the expensive cost of loading the entire graph and node embeddings. Besides, nonlinearity makes the optimization process a mystery. To this end, an enhanced LP method, called GraphHop, is proposed to tackle these problems. GraphHop can be viewed as a smoothening LP algorithm, in which each propagation alternates between two steps: label aggregation and label update. In the label aggregation step, multihop neighbor embeddings are aggregated to the center node. In the label update step, new embeddings are learned and predicted for each node based on aggregated results from the previous step. The two-step iteration improves the graph signal smoothening capacity. Furthermore, to encode attributes, links, and labels on graphs effectively under one framework, we adopt a two-stage training process, i.e., the initialization stage and the iteration stage. Thus, the smooth attribute information extracted from the initialization stage is consistently imposed in the propagation process in the iteration stage. Experimental results show that GraphHop outperforms state-of-the-art graph learning methods on a wide range of tasks in graphs of various sizes (e.g., multilabel and multiclass classification on citation networks, social graphs, and commodity consumption graphs).

A semi-supervised medical image classification method based on combined pseudo-labeling and distance metric consistency

A semi-supervised medical image classification method based on combined pseudo-labeling and distance metric consistency

Joint learning of feature and topology for multi-view graph convolutional network

Graph convolutional network has been extensively employed in semi-supervised classification tasks. Although some studies have attempted to leverage graph convolutional networks to explore multi-view data, they mostly consider the fusion of feature and topology individually, leading to the underutilization of the consistency and complementarity of multi-view data. In this paper, we propose an end-to-end joint fusion framework that aims to simultaneously conduct a consistent feature integration and an adaptive topology adjustment. Specifically, to capture the feature consistency, we construct a deep matrix decomposition module, which maps data from different views onto a feature space obtaining a consistent feature representation. Moreover, we design a more flexible graph convolution that allows to adaptively learn a more robust topology. A dynamic topology can greatly reduce the influence of unreliable information, which acquires a more adaptive representation. As a result, our method jointly designs an effective feature fusion module and a topology adjustment module, and lets these two modules mutually enhance each other. It takes full advantage of the consistency and complementarity to better capture the more intrinsic information. The experimental results indicate that our method surpasses state-of-the-art semi-supervised classification methods.

A Weak Sample Optimisation Method for Building Classification in a Semi-Supervised Deep Learning Framework

Deep learning has gained widespread interest in the task of building semantic segmentation modelling using remote sensing images; however, neural network models require a large number of training samples to achieve better classification performance, and the models are more sensitive to error patches in the training samples. The training samples obtained in semi-supervised classification methods need less reliable weakly labelled samples, but current semi-supervised classification research puts the generated weak samples directly into the model for applications, with less consideration of the impact of the accuracy and quality improvement of the weak samples on the subsequent model classification. Therefore, to address the problem of generating and optimising the quality of weak samples from training data in deep learning, this paper proposes a semi-supervised building classification framework. Firstly, based on the test results of the remote sensing image segmentation model and the unsupervised classification results of LiDAR point cloud data, this paper quickly generates weak image samples of buildings. Secondly, in order to improve the quality of the spots of the weak samples, an iterative optimisation strategy of the weak samples is proposed to compare and analyse the weak samples with the real samples and extract the accurate samples from the weak samples. Finally, the real samples, the weak samples, and the optimised weak samples are input into the semantic segmentation model of buildings for accuracy evaluation and analysis. The effectiveness of this paper’s approach was experimentally verified on two different building datasets, and the optimised weak samples improved by 1.9% and 0.6%, respectively, in the test accuracy mIoU compared to the initial weak samples. The results demonstrate that the semi-supervised classification framework proposed in this paper can be used to alleviate the model’s demand for a large number of real-labelled samples while improving the ability to utilise weak samples, and it can be used as an alternative to fully supervised classification methods in deep learning model applications that require a large number of training samples.

ReliaMatch: Semi-Supervised Classification with Reliable Match

Deep learning has been widely used in various tasks such as computer vision, natural language processing, predictive analysis, and recommendation systems in the past decade. However, practical scenarios often lack labeled data, posing challenges for traditional supervised methods. Semi-supervised classification methods address this by leveraging both labeled and unlabeled data to enhance model performance, but they face challenges in effectively utilizing unlabeled data and distinguishing reliable information from unreliable sources. This paper introduced ReliaMatch, a semi-supervised classification method that addresses these challenges by using a confidence threshold. It incorporates a curriculum learning stage, feature filtering, and pseudo-label filtering to improve classification accuracy and reliability. The feature filtering module eliminates ambiguous semantic features by comparing labeled and unlabeled data in the feature space. The pseudo-label filtering module removes unreliable pseudo-labels with low confidence, enhancing algorithm reliability. ReliaMatch employs a curriculum learning training mode, gradually increasing training dataset difficulty by combining selected samples and pseudo-labels with labeled data. This supervised approach enhances classification performance. Experimental results show that ReliaMatch effectively overcomes challenges associated with the underutilization of unlabeled data and the introduction of error information, outperforming the pseudo-label strategy in semi-supervised classification.

Perturbed peer model with joint confidence for semi-supervised object-based classification in urban area

ABSTRACT The application of deep learning (DL) improves the accuracy of object-based classification in urban area, but the huge numbers of labelled samples required for training DL models are difficult to obtain. To address that, we propose a novel semi-supervised object-based classification method that combines pseudo-labelling method and consistency regularization method, named as perturbed peer model (PPM). To evaluate the quality of unlabelled object samples, a new object-level joint confidence is designed to assess the confidence of the samples’ prediction, which provides guidance for selecting unlabelled object samples in semi-supervised object-based classification. Instead of only using the high-confidence samples as usual, both the high-confidence samples with discriminative power and the low-confidence samples with a large range of structural features are exploited using pseudo-labelling method and consistency regularization method, respectively, facilitating the fusion of the two methods in the proposed PPM. In addition, two types of perturbations, dropout and difference augmentation, are integrated into the model to drive the consistency regularization method as well as to enhance the difference to facilitate the pseudo-labelling method. Experimental results show that the classification accuracy of PPM is better than the widely-used self-training, co-training, noisy-student, unsupervised data augmentation for consistency training, and FreeMatch methods in urban area.

Graph neural network-based remote target classification in hyperspectral imaging

ABSTRACT Hyperspectral Imagery (HSI) onboard target classification is a frequently used technique in remote sensing. Due to the small volume of labelled data, the classification of HSI has been a challenging subject in recent study. The graph neural network (GNN) has become a popular method for semi-supervised classification, and its use with hyperspectral images has gained a lot of interest. A graph filter or single graph neural network has been typically employed in the earlier GNN-based approaches, and it is used to obtain HSI characteristics. It has not fully utilized the benefits of different graph filters or graph neural networks. The issue of oversmoothing also persists with the classical GNNs. We propose a spectral filter and an autoregressive moving average filter for the multi-graph neural network; (SAF-GNN) to address such drawbacks as the one mentioned above. The first is excellent at extracting the nodes’ spectral characteristics, and the second is effective at suppressing graph distortion. With the help of performance measures like overall accuracy (OA), individual class accuracy (ICA), and Kappa coefficient (KC), the performance of the proposed method was compared to that of other state-of-the-art methods. The result shows that the SAF-GNN provides an improvement in OA, ICA and KC of 2.21%, 7.93% and 0.025 for the cuprite dataset and 4.84%, 11.78% and 0.025 for the Pavia University dataset, respectively. Comparison results show that the proposed method is suitable for remote target classification problem.

WETLAND CHANGE DETECTION USING SENTINEL-2 IN THE PART OF LATVIA

In the article, the possible impact of changes on wetland were analysed by the semi-supervised classification method of statistical analysis. The Sentinel-2 raw data between two different seasons are combined together. The data preparation is shortly described in the article. Data is clustered with unsupervised method. The article describes a supervised method – how data credibility and classification can be estimated if its reference is poor quality.

A semi-supervised short text sentiment classification method based on improved Bert model from unlabelled data

Short text information has considerable commercial value and immeasurable social value. Natural language processing and short text sentiment analysis technology can organize and analyze short text information on the Internet. Natural language processing tasks such as sentiment classification have achieved satisfactory performance under a supervised learning framework. However, traditional supervised learning relies on large-scale and high-quality manual labels and obtaining high-quality label data costs a lot. Therefore, the strong dependence on label data hinders the application of the deep learning model to a large extent, which is the bottleneck of supervised learning. At the same time, short text datasets such as product reviews have an imbalance in the distribution of data samples. To solve the above problems, this paper proposes a method to predict label data according to semi-supervised learning mode and implements the MixMatchNL data enhancement method. Meanwhile, the Bert pre-training model is updated. The cross-entropy loss function in the model is improved to the Focal Loss function to alleviate the data imbalance in short text datasets. Experimental results based on public datasets indicate the proposed model has improved the accuracy of short text sentiment recognition compared with the previous update and other state-of-the-art models.

Semi-Supervised Learning for Medical Image Classification Based on Anti-Curriculum Learning

Although deep learning has achieved great success in image classification, large amounts of labelled data are needed to make full use of the advantages of deep learning. However, annotating a large number of images is expensive and time-consuming, especially annotating medical images, which requires professional knowledge. Therefore, semi-supervised learning has shown its potential for medical image classification. In this paper, we propose a novel pseudo-labelling semi-supervised learning method for medical image classification. Firstly, we utilize the anti-curriculum strategy for model training to prevent the model from producing predictions with a high value from the samples which are similar with existed labeled data. Secondly, to produce more stable and accurate pseudo labels for unlabeled data, we generate the pseudo labels with ensemble predictions provided by the model with samples augmented by different augmentations. In addition, we refine the generated pseudo labels using the prediction of the model at the current epoch in order to make the model learn from itself and improve the model performance. Comparative experiments on the Chest X-ray14 dataset for a multi-label classification task and the ISIC 2018 dataset for a multi-class classification task are performed, and the experimental results show the effectiveness of our method.

Semi-Supervised Land Cover Classification of Remote Sensing Imagery Using CycleGAN and EfficientNet

Image classification of very high resolution (VHR) images is a fundamental task in the remote sensing domain for various applications, such as land cover mapping, vegetation mapping, and urban planning. Recently, deep learning-based semantic segmentation networks demonstrated the promising performance for pixel-level image classification. However, deep learning-based approaches are generally limited by the requirement of a sufficient amount of labeled data to obtain stable accuracy, and acquiring reference labels of remotely-sensed VHR images is very labor-extensive and expensive. Hence, this paper applied a semi-supervised learning-based CycleGAN and EfficientNet for VHR remote sensing image classification to overcome this problem. The proposed method achieved the highest accuracy than the other benchmarks. The largest increase in accuracy was observed in a test site containing complex objects due to the regularization effect of the semi-supervised method using unlabeled data. Moreover, results indicated that a relatively sufficient amount of unlabeled data compared with labeled data are required to increase the classification accuracy by controlling the amount of labeled and unlabeled data. Finally, we verified that the semi-supervised method returned significantly improved results irrespective of the three classification network structures, displaying the applicability of the method for semi-supervised image classification on remotely-sensed VHR images.

Semi-Supervised Classification of PolSAR Images Based on Co-Training of CNN and SVM with Limited Labeled Samples.

Recently, convolutional neural networks (CNNs) have shown significant advantages in the tasks of image classification; however, these usually require a large number of labeled samples for training. In practice, it is difficult and costly to obtain sufficient labeled samples of polarimetric synthetic aperture radar (PolSAR) images. To address this problem, we propose a novel semi-supervised classification method for PolSAR images in this paper, using the co-training of CNN and a support vector machine (SVM). In our co-training method, an eight-layer CNN with residual network (ResNet) architecture is designed as the primary classifier, and an SVM is used as the auxiliary classifier. In particular, the SVM is used to enhance the performance of our algorithm in the case of limited labeled samples. In our method, more and more pseudo-labeled samples are iteratively yielded for training through a two-stage co-training of CNN and SVM, which gradually improves the performance of the two classifiers. The trained CNN is employed as the final classifier due to its strong classification capability with enough samples. We carried out experiments on two C-band airborne PolSAR images acquired by the AIRSAR systems and an L-band spaceborne PolSAR image acquired by the GaoFen-3 system. The experimental results demonstrate that the proposed method can effectively integrate the complementary advantages of SVM and CNN, providing overall classification accuracy of more than 97%, 96% and 93% with limited labeled samples (10 samples per class) for the above three images, respectively, which is superior to the state-of-the-art semi-supervised methods for PolSAR image classification.

A Novel Semi-Supervised Dynamic Classifier Selection Method for HSI Classification Based on SP Segmentation

A Novel Semi-Supervised Dynamic Classifier Selection Method for HSI Classification Based on SP Segmentation

Neighbor-Guided Consistent and Contrastive Learning for Semi-Supervised Action Recognition.

Semi-supervised learning has been well established in the area of image classification but remains to be explored in video-based action recognition. FixMatch is a state-of-the-art semi-supervised method for image classification, but it does not work well when transferred directly to the video domain since it only utilizes the single RGB modality, which contains insufficient motion information. Moreover, it only leverages highly-confident pseudo-labels to explore consistency between strongly-augmented and weakly-augmented samples, resulting in limited supervised signals, long training time, and insufficient feature discriminability. To address the above issues, we propose neighbor-guided consistent and contrastive learning (NCCL), which takes both RGB and temporal gradient (TG) as input and is based on the teacher-student framework. Due to the limitation of labelled samples, we first incorporate neighbors information as a self-supervised signal to explore the consistent property, which compensates for the lack of supervised signals and the shortcoming of long training time of FixMatch. To learn more discriminative feature representations, we further propose a novel neighbor-guided category-level contrastive learning term to minimize the intra-class distance and enlarge the inter-class distance. We conduct extensive experiments on four datasets to validate the effectiveness. Compared with the state-of-the-art methods, our proposed NCCL achieves superior performance with much lower computational cost.

A Robust Fault Classification Method for Streaming Industrial Data Based on Wasserstein Generative Adversarial Network and Semi-Supervised Ladder Network

With the development of modern information technology, the collection, storage and transmission of information in the process industry has been gaining popularity. However, the massive streaming industrial data obtained in real time has some non-ideal characteristics, such as lack of labels and missing values, which greatly increases the difficulty of process monitoring in process industry. Therefore, a robust semi-supervised fault classification method is proposed in this paper. First, Wasserstein generative adversarial network (WGAN) and enhanced minimal gated unit (EMGU) are integrated to complete the missing data imputation of the incomplete unlabeled streaming industrial data, and then semi-supervised ladder network (SLN) is trained with the imputed unlabeled data and complete labeled data for fault classification. A case study on the hot rolling process demonstrates that the proposed method shows outstanding modeling and classification performance in lack of labeled data and missing data, compared to the other state-of-art deep learning methods.

Accelerating Semi-Supervised Text Classification by K-Way Projecting Networks

The state of the art semi-supervised learning framework has greatly shown its potential in making deep and complex language models such as BERT highly effective for text classification tasks when labeled data is limited. However, the large size and low inference speed of such models may hinder their application on resources-limited or real-time use cases. In this paper, we propose a new approach in semi-supervised learning framework to distill large complex teacher model into a fairly lightweight student model which has the ability of acquiring knowledge from different layers of teacher with the usage of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$K$ </tex-math></inline-formula> -way projecting networks. Across four English datasets in text classification benchmarks and one dataset collected from an Chinese online course, our experiment shows that this student model achieves comparable results with the state of the art Transformer-based semi-supervised text classification methods, while using only 0.156MB parameters and having an inference speed 785 times faster than the teacher model.

An Hybrid Ontology Matching Mechanism for Adaptive Educational eLearning Environments

Providing the same pedagogical and educational methods to all students is pedagogically ineffective. In contrast, the pedagogical strategies that adapt to the fundamental individual skills of the students have proved to be more effective. An important innovation in this direction is the adaptive educational systems (AESs) that adjust the teaching content on educational needs and students’ skills. Effective utilization of these approaches can be enhanced with artificial intelligence (AI) and semantic web technologies that can increase data generation, access, flow, integration, and comprehension using the same open standards driving the World Wide Web. This study proposes a novel adaptive educational eLearning system (AEeLS) that can gather and analyze data from learning repositories and adapt these to the educational curriculum according to the student’s skills and experience. It is an innovative hybrid machine learning system that combines a semi-supervised classification method for ontology matching and a recommendation mechanism that uses a sophisticated way from neighborhood-based collaborative and content-based filtering techniques to provide a personalized educational environment for each student.

Editorial

Dear Readers, At the end of this year, it gives me great pleasure to announce the tenth regular issue of 2022. In this issue, various topical aspects of computer science are covered in 4 articles by 10 authors from 4 countries in 4 articles. I would like to thank all the authors for their sound research papers and the editorial board for the highly valuable review effort and comments for improvement. These contributions, together with the generous support of the consortium members, sustain the quality of our journal. I am looking forward to continuing my work as Managing Editor-in-Chief with the J.UCS community. In an ongoing effort to further strengthen our journal, I would like to expand the editorial board: If you are a tenured associate professor or above with a strong publication record, you are welcome to apply to join our editorial board. We are also interested in high-quality proposals for special issues on new topics and trends. Please consider yourself and encourage your colleagues to submit high-quality articles or special issue proposals for our journal. In this regular issue, I am very pleased to introduce the following 4 accepted articles: Nibras Othman Abdulwahid, Sana Fakhfakh and Ikram Amous from Tunisia present their research and proposal for simulating and predicting students&amp;rsquo; academic performance based on two models, the seven-subject, one-grade, one-output (SOO) and the seven-subject, twelve-year, seven-output (STS) model. Jorge R. Qui&amp;ntilde;ones and Antonio J. Fern&amp;aacute;ndez-Leiva from Spain introduce their approach to automated video gaming parameter tuning based on an extension of XVGDL, a language for specifying video games. Jarashanth Selvarajah and Ruwan Nawarathna from Sri Lanka build an automated drug monitoring and surveillance system for social media based on embedding-level attention, convolutional neural networks (CNN), and bidirectional gated recurrent units (BiGRU). Marko Zekan, Igor Tomi&amp;#269;i&amp;#263; and Markus Schatten from Croatia discuss their research of an improved Network Intrusion Detection System (NIDS) applying a novel semi-supervised EC-GAN method for network flow classification. Season greetings to all of you, relaxing holidays and &amp;lsquo;Enjoy Reading&amp;rsquo;!

Time-frequency based multi-task learning for semi-supervised time series classification

Semi-supervised learning is crucial for alleviating labeling burdens in time series classification. Most of the existing semi-supervised time series classification methods extract patterns from the time domain, ignoring the time-frequency domain and the latent feature space shared by the labeled and unlabeled samples. For that, a Multi-task learning scheme based on Time-Frequency mining for semi-supervised time series Classification (MTFC) is proposed. First, we design a series of unsupervised tasks for capturing time-frequency information. Considering the consistency between labeled and unlabeled data, we then employ a multi-task learning framework to learn their common features. Meanwhile, we theoretically analyze the proposed semi-supervised classification method and provide a novel generalization result for the MTFC. Extensive experiments on multiple time series datasets demonstrate that our MTFC can effectively improve the performance of semi-supervised classification and achieve state-of-the-art results.

Semi-supervised learning with graph convolutional extreme learning machines

Extreme 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 information among data and resulting in poor robustness. In this paper, we present a novel semi-supervised learning framework, termed Graph Convolutional Extreme Learning Machines (GCELM), based on extending the traditional ELM to the non-Euclidean domain. Technically, we recast ELM layers into a randomized graph convolutional embedding layer followed by a graph convolutional regression layer, which endows ELM with the capability to handle graphs in the non-Euclidean domain. Benefiting from the diversity of the randomized graph convolution, we further propose an enhanced GCELM, i.e., Voting-based GCELM (V-GCELM), by using a simple voting ensemble strategy. The proposed methods preserve the advantages of ELMs, thus being more efficient than the gradient-based graph convolutional networks but without loss of graph learning ability. Extensive experiments on 36 benchmark datasets demonstrate that the proposed methods significantly outperform many previous semi-supervised classification methods.