Semi-supervised Classification Research Articles

The Dual Mahalanobis-kernel LSSVM for Semi-supervised Classification in Disease Diagnosis

The Dual Mahalanobis-kernel LSSVM for Semi-supervised Classification in Disease Diagnosis

MiGIS: micromorphological soil and sediment thin section analysis using an open-source GIS and machine learning approach

Abstract. ​​​​​​​Micromorphological analysis using a petrographic microscope is one of the conventional methods to characterise microfacies in rocks (sediments) and soils. This analysis of the composition and structure observed in thin sections (TSs) yields seminal, but primarily qualitative, insights into their formation. In this context, the following question arises: how can micromorphological features be measured, classified, and particularly quantified to enable comparisons beyond the micro scale? With the Micromorphological Geographic Information System (MiGIS), we have developed a Python-based toolbox for the open-source software QGIS 3, which offers a straightforward solution to digitally analyse micromorphological features in TSs. By using a flatbed scanner and (polarisation) film, high-resolution red–green–blue (RGB) images can be captured in transmitted light (TL), cross-polarised light (XPL), and reflected light (RL) mode. Merging these images in a multi-RGB raster, feature-specific image information (e.g. light refraction properties of minerals) can be combined in one data set. This provides the basis for image classification with MiGIS. The MiGIS classification module uses the random forest algorithm and facilitates a semi-supervised (based on training areas) classification of the feature-specific colour values (multi-RGB signatures). The resulting classification map shows the spatial distribution of thin section features and enables the quantification of groundmass, pore space, minerals, or pedofeatures, such nodules being dominated by iron oxide and clay coatings. We demonstrate the advantages and limitations of the method using TSs from a loess–palaeosol sequence in Rheindahlen (Germany), which was previously studied using conventional micromorphological techniques. Given the high colour variance within the feature classes, MiGIS appears well-suited for these samples, enabling the generation of accurate TS feature maps. Nevertheless, the classification accuracy can vary due to the TS quality and the academic training level, in micromorphology and in terms of the classification process, when creating the training data. However, MiGIS offers the advantage of quantifying micromorphological features and analysing their spatial distribution for entire TSs. This facilitates reproducibility, visualisation of spatial relationships, and statistical comparisons of composition among distinct samples (e.g. related sediment layers).

NUNI-Waste: novel semi-supervised semantic segmentation waste classification with non-uniform data augmentation

Waste categorization and recycling are critical approaches for converting waste into valuable and functional materials, thereby significantly aiding in land preservation, reducing pollution, and optimizing resource usages. However, real-world classification and identification of recyclable waste face substantial hurdles due to the intricate and unpredictable nature of wastes, as well as the limited availability of comprehensive waste datasets. These factors limit efficacy of the existing research work in the domain of waste management. In this paper, we utilize semantic segmentation at individual pixel level and introduce a semi-supervised metod for authentic waste classification scenarios, leveraging the Zerowaste dataset. We devise a non-standard data augmentation strategy that mimics the ever-changing conditions of real-world waste environments. Additionally, we introduce an adaptive weighted loss function and dynamically adjust the ratio of positive to negative samples through a masking method, ensuring the model learns from relevant samples. Lastly, to maintain consistency between predictions made on data-augmented images and the original counterparts, we remove input perturbations. Our method proves to be effective, as verified by an array of standard experiments and ablation studies, achieved an accuracy improvement of 3.74% over the baseline Zerowaste method.

Discriminative and robust least squares regression for semi-supervised image classification

Due to the ability to leverage information from both unlabeled and labeled data, semi-supervised classification has found extensive applications in various practical scenarios. However, there are two major drawbacks: (1) Traditional graph construction leads to high algorithmic complexity, which limits efficiency. (2) The decision boundary might be blurred by boundary points in common cases. To cope with these issues, inspired by classical Least Squares Regression (LSR), we present a novel semi-supervised classification algorithm termed as Discriminative and Robust LSR (DRLSR) for semi-supervised image classification. First of all, a manifold regularization term is designed and introduced to an LSR-based semi-supervised method to preserve local manifold structures and smooth structures of the subspace, which strengthens the discrimination ability. Meanwhile, preservation of local manifold structures also contributes to restrain decision boundaries from being blurred by boundary points, which strengthens robustness of the algorithm. After that, an efficient alternative optimization method is applied to our algorithm. Evidence of the effectiveness of DRLSR are compelled by extensive experimental results.

Refined Semi-Supervised Modulation Classification: Integrating Consistency Regularization and Pseudo-Labeling Techniques

Automatic modulation classification (AMC) plays a crucial role in wireless communication by identifying the modulation scheme of received signals, bridging signal reception and demodulation. Its main challenge lies in performing accurate signal processing without prior information. While deep learning has been applied to AMC, its effectiveness largely depends on the availability of labeled samples. To address the scarcity of labeled data, we introduce a novel semi-supervised AMC approach combining consistency regularization and pseudo-labeling. This method capitalizes on the inherent data distribution of unlabeled data to supplement the limited labeled data. Our approach involves a dual-component objective function for model training: one part focuses on the loss from labeled data, while the other addresses the regularized loss for unlabeled data, enhanced through two distinct levels of data augmentation. These combined losses concurrently refine the model parameters. Our method demonstrates superior performance over established benchmark algorithms, such as decision trees (DTs), support vector machines (SVMs), pi-models, and virtual adversarial training (VAT). It exhibits a marked improvement in the recognition accuracy, particularly when the proportion of labeled samples is as low as 1–4%.

Soil Classification Mapping Using a Combination of Semi-Supervised Classification and Stacking Learning (SSC-SL)

In digital soil mapping, machine learning models have been widely applied. However, the accuracy of machine learning models can be limited by the use of a single model and a small number of soil samples. This study introduces a novel method, semi-supervised classification combined with stacking learning (SSC-SL), to enhance soil classification mapping in hilly and low-mountain areas of Northern Jurong City, Jiangsu Province, China. This study incorporated Gaofen-2 (GF-2) remote sensing imagery along with its associated remote sensing indices, the ALOS Digital Elevation Model (DEM) and their derived topographic factors, and soil parent material data in its modelling process. We first used three base learners, Ranger, Rpart, and XGBoost, to construct the SL model. In addition, we employed the fuzzy c-means clustering algorithm (FCM) to construct a clustering map. To fully leverage the information from a multitude of environmental variables, understand the distribution of data, and enhance the effectiveness of the classification, we selected unlabelled samples near the boundaries of the patches on the clustering map. The SSC-SL model demonstrated superior stability and performance, with optimal accuracy at a 0.9 confidence level, achieving an overall accuracy of 0.77 and a kappa coefficient of 0.73. These metrics exceeded those of the highest performing base learner (Ranger model) by 10.4% and 12.3%, respectively, and they outperformed the least effective base learner (Rpart model) by 27.3% and 32.9%. It notably improves the spatial distribution accuracy of soil types. Key environmental variables influencing soil type distribution include soil parent material (SPM), land use (LU), the multi-resolution valley bottom flatness index (MRVBF), and Elevation (Ele). In conclusion, the SSC-SL model offers a novel and effective approach for enhancing the predictive accuracy of soil classification mapping.

Towards Robust Learning with Noisy and Pseudo Labels for Text Classification

Unlike Positive Training (PT), Negative Training (NT) is an indirect learning technique that trains the model on a combination of clean and noisy data using complementary labels, which are randomly generated from the label space except for the actual label. Although clean samples have identical distributions to the test samples, they are treated with the same level of uncertainty as noisy samples because of the complementary labeling of NT. Consequently, their contribution to the overall performance is relatively lower. We propose a Learning with Noisy and Pseudo Label (LNPL) framework, which jointly trains the model using PT and NT on clean and noisy data, respectively. We aim to enable direct learning on clean samples while leveraging the robustness of NT against noise in a unified framework. To mitigate the abundance of noisy instances, we leverage a gradient reversal layer at the top of LNPL as a regularization term to mislead the recognition of the source of the instance (e.g., clean or noisy). Moreover, we introduce a self-training LNPL that performs a semi-supervised text classification task as a learning with noisy pseudo-label problem. Extensive experiments on various textual benchmark datasets demonstrate that LNPL is robust and consistently outperforms the alternatives. The code is available on GitHub.1

FPGA-based remote target classification in hyperspectral imaging using multi-graph neural network

Hyperspectral imagery (HSI) is widely used in remote sensing for target classification; however, its accurate classification remains challenging due to the scarcity of labeled data. Graph Neural Networks (GNNs) have emerged as a popular method for semi-supervised classification, attracting significant interest in the context of HSI analysis. Nevertheless, conventional GNN-based approaches often rely on a single graph filter to extract HSI characteristics, failing to fully exploit the potential benefits of different graph filters. Additionally, oversmoothing issues plague classical GNNs, further affecting classification performance. To address these drawbacks, we propose a novel approach called Spectral and Autoregressive Moving Average Graph Filter for the Multi-Graph Neural Network (SAM-GNN). This approach leverages two distinct graph filters: one specialized in extracting the spectral characteristics of nodes and the other effectively suppressing graph distortion. Through extensive evaluations, we compare the performance of SAM-GNN with other state-of-the-art methods, employing metrics such as overall accuracy (OA), individual class accuracy (IA), and Kappa coefficient (KC). The results shows that the SAM-GNN provides an improvement in KC, IA, and OA of 6.71%, 5.7%, and 3.93% for the Pavia University dataset and 4.67%, 3.67%, and 3.49% for the Cuprite dataset respectively. Furthermore, we implement SAM-GNN on the Virtex-7 field-programmable gate array (FPGA), demonstrating that the method achieves highly accurate target localization results, bringing us closer to real-world applications in HSI classification.

Dynamic Weighted Adversarial Learning for Semi-Supervised Classification under Intersectional Class Mismatch

Nowadays, class-mismatch problem has drawn intensive attention in Semi-Supervised Learning (SSL), where the classes of labeled data are assumed to be only a subset of the classes of unlabeled data. However, in a more realistic scenario, the labeled data and unlabeled data often share some common classes while they also have their individual classes, which leads to an “intersectional class-mismatch” problem. As a result, existing SSL methods are often confused by these individual classes and suffer from performance degradation. To address this problem, we propose a novel Dynamic Weighted Adversarial Learning (DWAL) framework to properly utilize unlabeled data for boosting the SSL performance. Specifically, to handle the influence of the individual classes in unlabeled data (i.e., Out-Of-Distribution classes), we propose an enhanced adversarial domain adaptation to dynamically assign weight for each unlabeled example from the perspectives of domain adaptation and a class-wise weighting mechanism, which consists of transferability score and prediction confidence value. Besides, to handle the influence of the individual classes in labeled data (i.e., private classes), we propose a dissimilarity maximization strategy to suppress the inaccurate correlations caused by the examples of individual classes within labeled data. Therefore, our DWAL can properly make use of unlabeled data to acquire an accurate SSL classifier under intersectional class-mismatch setting, and extensive experimental results on five public datasets demonstrate the effectiveness of the proposed model over other state-of-the-art SSL methods.

Contrastive learning of graphs under label noise

In the domain of graph-structured data learning, semi-supervised node classification serves as a critical task, relying mainly on the information from unlabeled nodes and a minor fraction of labeled nodes for training. However, real-world graph-structured data often suffer from label noise, which significantly undermines the performance of Graph Neural Networks (GNNs). This problem becomes increasingly severe in situations where labels are scarce. To tackle this issue of sparse and noisy labels, we propose a novel approach Contrastive Robust Graph Neural Network (CR-GNN), Firstly, considering label sparsity and noise, we employ unsupervised contrastive loss and further incorporate homophily in the graph structure, thus introducing neighbor contrastive loss. Moreover, data augmentation is typically used to construct positive and negative samples in contrastive learning, which may result in inconsistent prediction outcomes. Based on this, we propose a dynamic cross-entropy loss, which selects the nodes with consistent predictions as reliable nodes for cross-entropy loss and benefits to mitigate the overfitting to labeling noise. Finally, we propose cross-space consistency to narrow the semantic gap between the contrast and classification spaces. Extensive experiments on multiple publicly available datasets demonstrate that CR-GNN notably outperforms existing methods in resisting label noise.

Multimodal graph learning based on 3D Haar semi-tight framelet for student engagement prediction

With the increasing availability of multimodal educational data, there is a growing need to effectively integrate and exploit multiple data sources to enhance student engagement prediction accuracy. In this work, we propose a framework that combines multimodal data, including visual, textual and acoustic modalities that reflect the students’ personalities, their demographic information, their learning behavior and attention, with graph learning techniques. Specifically, 3D Haar semi-tight framelet transforms are developed to capture the inter-modal relationships and model the complex interactions within the multimodal data. Subsequently, we introduce a novel module for adaptive graph structure learning based on the spectrum of multimodal data, which takes into consideration the distinct contributions of low-pass and high-pass framelet coefficients by adaptively weighing their impact. By addressing a standard semi-supervised node classification problem, we successfully achieve the objective of student engagement prediction. The experiment evaluations on a real-world educational dataset demonstrate the effectiveness of the proposed approach, achieving superior performance compared to state-of-the-art methods. Our experimental studies demonstrate the importance of multimodal graph learning in accurately predicting student engagement and its potential to enhance educational outcomes.

DAHGN: Degree-Aware Heterogeneous Graph Neural Network

In recent years, Graph Neural Networks (GNNs), an emerging technology for learning from graph-structured data, have attracted much attention. Despite the widespread applications of GNNs across diverse domains, recent studies have shown that insufficient information aggregation for low-degree nodes (i.e., tail nodes) leads to inferior performance of GNNs. While numerous recent studies have aimed to address the issue of degree bias in homogeneous graphs, there are limited studies on analyzing such unfairness for heterogeneous information networks. In this article, we propose a novel semi-supervised contrastive learning framework named Degree-Aware Heterogeneous Graph Neural Network (DAHGN), which achieves promising performance by alleviating the degree bias. In brief, we first construct two contrastive graph views, one from a heterogeneous graph that focuses on capturing complementary information to enhance the node representations and one from an extracted homogeneous subgraph that focuses on applying different strategies to low- and high- degree nodes to eliminate the degree bias. We then leverage the label learned from the heterogeneous view to reconstruct the positive node pairs in the contrastive learning framework. Finally, we combine the task loss (semi-supervised) and the contrastive loss to optimize the model performance. We conduct extensive experiments on benchmark datasets to validate the effectiveness of our model, and the results demonstrate that the DAHGN outperforms a wide range of state-of-the-art methods in the semi-supervised node classification problem.

DisenSemi: Semi-Supervised Graph Classification via Disentangled Representation Learning.

Graph classification is a critical task in numerous multimedia applications, where graphs are employed to represent diverse types of multimedia data, including images, videos, and social networks. Nevertheless, in the real world, labeled graph data are always limited or scarce. To address this issue, we focus on the semi-supervised graph classification task, which involves both supervised and unsupervised models learning from labeled and unlabeled data. In contrast to recent approaches that transfer the entire knowledge from the unsupervised model to the supervised one, we argue that an effective transfer should only retain the relevant semantics that align well with the supervised task. We introduce a novel framework termed in this article, which learns disentangled representation for semi-supervised graph classification. Specifically, a disentangled graph encoder is proposed to generate factorwise graph representations for both supervised and unsupervised models. Then, we train two models via supervised objective and mutual information (MI)-based constraints, respectively. To ensure the meaningful transfer of knowledge from the unsupervised encoder to the supervised one, we further define an MI-based disentangled consistency regularization between two models and identify the corresponding rationale that aligns well with the current graph classification task. Experiments conducted on various publicly available datasets demonstrate the effectiveness of our .

Towards Semi-Supervised Universal Graph Classification

Graph neural networks have pushed state-of-the-arts in graph classifications recently. Typically, these methods are studied within the context of supervised end-to-end training, which necessities copious task-specific labels. However, in real-world circumstances, labeled data could be limited, and there could be a massive corpus of unlabeled data, even from unknown classes as a complementary. Towards this end, we study the problem of semi-supervised universal graph classification, which not only identifies graph samples which do not belong to known classes, but also classifies the remaining samples into their respective classes. This problem is challenging due to a severe lack of labels and potential class shifts. In this paper, we propose a novel graph neural network framework named UGNN, which makes the best of unlabeled data from the subgraph perspective. To tackle class shifts, we estimate the certainty of unlabeled graphs using multiple subgraphs, which facilities the discovery of unlabeled data from unknown categories. Moreover, we construct semantic prototypes in the embedding space for both known and unknown categories and utilize posterior prototype assignments inferred from the Sinkhorn-Knopp algorithm to learn from abundant unlabeled graphs across different subgraph views. Extensive experiments on six datasets verify the effectiveness of UGNN in different settings.

SemiRS-COC: Semi-Supervised Classification for Complex Remote Sensing Scenes with Cross-Object Consistency.

Semi-supervised learning (SSL), which aims to learn with limited labeled data and massive amounts of unlabeled data, offers a promising approach to exploit the massive amounts of satellite Earth observation images. The fundamental concept underlying most state-of-the-art SSL methods involves generating pseudo-labels for unlabeled data based on image-level predictions. However, complex remote sensing (RS) scene images frequently encounter challenges, such as interference from multiple background objects and significant intra-class differences, resulting in unreliable pseudo-labels. In this paper, we propose the SemiRS-COC, a novel semi-supervised classification method for complex RS scenes. Inspired by the idea that neighboring objects in feature space should share consistent semantic labels, SemiRS-COC utilizes the similarity between foreground objects in RS images to generate reliable object-level pseudo-labels, effectively addressing the issues of multiple background objects and significant intra-class differences in complex RS images. Specifically, we first design a Local Self-Learning Object Perception (LSLOP) mechanism, which transforms multiple background objects interference of RS images into usable annotation information, enhancing the model's object perception capability. Furthermore, we present a Cross-Object Consistency Pseudo-Labeling (COCPL) strategy, which generates reliable object-level pseudo-labels by comparing the similarity of foreground objects across different RS images, effectively handling significant intra-class differences. Extensive experiments demonstrate that our proposed method achieves excellent performance compared to state-of-the-art methods on three widely-adopted RS datasets.

Semi-Supervised Scene Classification for Optical Remote Sensing Images via Label and Embedding Consistency

Semi-Supervised Scene Classification for Optical Remote Sensing Images via Label and Embedding Consistency

Semi-supervised Few-shot Classification with Multi-task Learning and Iterative Label Correction

Semi-supervised Few-shot Classification with Multi-task Learning and Iterative Label Correction

Joint Energy-based Model for Semi-supervised Respiratory Sound Classification: A Method of Insensitive to Distribution Mismatch.

Semi-supervised learning effectively mitigates the lack of labeled data by introducing extensive unlabeled data. Despite achieving success in respiratory sound classification, in practice, it usually takes years to acquire a sufficiently sizeable unlabeled set, which consequently results in an extension of the research timeline. Considering that there are also respiratory sounds available in other related tasks, like breath phase detection and COVID-19 detection, it might be an alternative manner to treat these external samples as unlabeled data for respiratory sound classification. However, since these external samples are collected in different scenarios via different devices, there inevitably exists a distribution mismatch between the labeled and external unlabeled data. For existing methods, they usually assume that the labeled and unlabeled data follow the same data distribution. Therefore, they cannot benefit from external samples. To utilize external unlabeled data, we propose a semi-supervised method based on Joint Energy-based Model (JEM) in this paper. During training, the method attempts to use only the essential semantic components within the samples to model the data distribution. When non-semantic components like recording environments and devices vary, as these non-semantic components have a small impact on the model training, a relatively accurate distribution estimation is obtained. Therefore, the method exhibits insensitivity to the distribution mismatch, enabling the model to leverage external unlabeled data to mitigate the lack of labeled data. Taking ICBHI 2017 as the labeled set, HF_Lung_V1 and COVID-19 Sounds as the external unlabeled sets, the proposed method exceeds the baseline by 12.86.

Impact of an eddy dipole of the Mozambique channel on mesopelagic organisms, highlighted by multifrequency backscatter classification.

The impact of a cyclonic (C), an anticyclonic (AC) eddy and transition zone (TZ), which is the area between the two eddies, on acoustic groups representing various mesopelagic organisms, was investigated using a semi-supervised multifrequency classification approach (hereafter, Escore algorithm). The Escore algorithm involved selecting regions of interest (ROIs) within multifrequency (18, 38, 70, and 120 kHz) echograms and classifying into four clusters or echo-classes using Sv differences (Sv18-38, Sv70-38, and Sv120-38). Acoustic densities and diel vertical migration strength varied between the AC, C, and TZ according to the frequency. The vertical stratification of temperature, salinity and fluorescence within the oceanographic structures had varied influences on the vertical structure of each echo-class which represent zooplankton-like organisms, small and large fish with swimbladders, and small and large siphonophores with pneumatophores. The echo-classes within the C were influenced by surface fluorescence, whereas in the AC and TZ, the echo-classes were influenced by deeper fluorescence and strong EKE. Our study provides new insights into the environmental variables within mesoscale and sub-mesoscale features impacting different groups of mesopelagic communities in the Indian Ocean.

Dual-Stream Class-Adaptive Network for Semi-Supervised Hyperspectral Image Classification

Dual-Stream Class-Adaptive Network for Semi-Supervised Hyperspectral Image Classification