Cost-Sensitive Canonical Correlation Analysis for Semi-Supervised Multi-View Learning

Ensemble learning has been widely used in data mining and pattern recognition. However, when the number of labeled data samples is very small, it is difficult to train a base classifier for ensemble learning, therefore, it is necessary to utilize an abundance of unlabeled data effectively. In most semi-supervised ensemble methods, the label prediction of unlabeled data and their use as pseudo-label data are common processes. However, the low accuracy of the label prediction of unlabeled data limits the ability to obtain improved ensemble members. In this paper, we propose effective ensemble learning methods for semi-supervised classification that combine label propagation and ensemble learning. We show that accurate ensemble members can be constructed using class labels predicted by a label propagation method, and unlabeled data samples are fully utilized for diverse ensemble member construction. Extensive experimental results demonstrate the performance of the proposed methods.

Synthetic semi-supervised learning in imbalanced domains: Constructing a model for donor-recipient matching in liver transplantation

We propose a new transductive label propagation method, termed Adaptive Neighborhood Propagation (Adaptive-NP) by joint L2,1-norm regularized sparse coding, for semi-supervised classification. To make the predicted soft labels more accurate for predicting the labels of samples and to avoid the tricky process of choosing the optimal neighborhood size or kernel width for graph construction, Adaptive-NP seamlessly integrates sparse coding and neighborhood propagation into a unified framework. That is, the sparse reconstruction error and classification error are combined for joint minimization, which clearly differs from traditional methods that explicitly separate graph construction and label propagation into independent steps, which may result in inaccurate predictions. Note that our Adaptive-NP alternately optimize the sparse codes and soft labels matrices, where the sparse codes are used as adaptive weights for neighborhood propagation at each iteration, so the tricky process of determining neighborhood size or kernel width is avoided. Besides, for enhancing sparse coding, we use the L2,1-norm constraint on the sparse coding coefficients and the reconstruction error at the same time for delivering more accurate and robust representations. Extensive simulations show that our model can deliver state-of-the-art performances on several public datasets for classification.

Label propagation is an essential semi-supervised learning method based on graphs, which has a broad spectrum of applications in pattern recognition and data mining. This paper proposes a quantum semi-supervised classifier based on label propagation. Considering the difficulty of graph construction, we develop a variational quantum label propagation (VQLP) method. In this method, a locally parameterized quantum circuit is created to reduce the parameters required in the optimization. Furthermore, we design a quantum semi-supervised binary classifier based on hybrid Bell and Z bases measurement, which has a shallower circuit depth and is more suitable for implementation on near-term quantum devices. We demonstrate the performance of the quantum semi-supervised classifier on the Iris data set, and the simulation results show that the quantum semi-supervised classifier has higher classification accuracy than the swap test classifier. This work opens a new path to quantum machine learning based on graphs.

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).

We propose a robust inductive semi-supervised label prediction model over the embedded representation, termed adaptive embedded label propagation with weight learning (AELP-WL), for classification. AELP-WL offers several properties. First, our method seamlessly integrates the robust adaptive embedded label propagation with adaptive weight learning into a unified framework. By minimizing the reconstruction errors over embedded features and embedded soft labels jointly, our AELP-WL can explicitly ensure the learned weights to be joint optimal for representation and classification, which differs from most existing LP models that perform weight learning separately by an independent step before label prediction. Second, existing models usually precalculate the weights over the original samples that may contain unfavorable features and noise decreasing performance. To this end, our model adds a constraint that decomposes original data into a sparse component encoding embedded noise-removed sparse representations of samples and a sparse error part fitting noise, and then performs the adaptive weight learning over the embedded sparse representations. Third, our AELP-WL computes the projected soft labels by trading-off the manifold smoothness and label fitness errors over the adaptive weights and the embedded representations for enhancing the label estimation power. By including a regressive label approximation error for simultaneous minimization to correlate sample features with the embedded soft labels, the out-of-sample issue is naturally solved. By minimizing the reconstruction errors over features and embedded soft labels, classification error and label approximation error jointly, state-of-the-art results are delivered.

In this paper, a novel multimedia data (specifically facial images) label propagation method is presented that is based on the inclusion of labelling constraints in the objective function of the MLPP-CLP state of the art algorithm. The proposed method can incorporate pairwise facial image similarity and dissimilarity constraints into the objective function of the aforementioned method. Experiments which have been conducted on facial image labelling in three stereoscopic movies, confirm the increased labelling accuracy of the proposed method.

A new method is proposed for change analysis with weight of significance between two multi-temporal multi-spectral images.This method gives us areas which indicate the assigned temporal change, for example, from vegetation to bare soil. Image dataare projected onto a feature space in which the assigned change is emphasized, and temporal changes between two images aredetected with suppression ofirrelevant changes. The validity ofthe method is confirmed by numerical simulation. The methodis successfully applied to actual multi-temporal and multi-spectral images. 1. INTRODUCTION Change analysis is one of the most important processings for monitoring environment. It provides us with information aboutchange, for example, of natural environment to urban area. In change analysis, it is required to analyze the particular changerather than to detect all types of change. There have been a lot of methods reported for change detection[1]. Most of them,however, detect all types of change without specifying the change[2], or analyze the changes categorically using supervisedclassification of two multi-temporal images[3][4]. In the former, the change to be analyzed is detected indirectly using cluster-ing, and in the latter, classification error is serious. A direct method has been required.We propose a method PACE (Particular Change Extractor) for analyzing temporal change with weight of significance. Themethod PACE enables us to select a particular type of change such as from vegetation to bare soil, and extracts areas in whichspectral pattern has the particular change between two multi-temporal and multi-spectral images. The method consists of threeprocedures; data projection, change detection and suppression of irrelevant changes. In the first two, we produce a feature spacederived from an assigned change so that the change is emphasized. Canonical correlation analysis[5] is used for it. We projecta set of image data onto the feature space. The difference between two transformed image data indicates temporal changes. As

Prediction of Alzheimer's diagnosis using semi-supervised distance metric learning with label propagation

On the technical side, both traditional, shallow feature-based methods (e.g., Support Vector Machines and Random Forest) and deep neural network models (e.g., LSTM and CNN types) have been utilized (Khare et al., 2024;Pepa et al., 2023). A key focus has been the development of multimodal systems that integrate diverse data sources, such as facial expressions, voice tone, dialogue sentiment, and physiological signals (Geetha et al., 2024). Multiple signals enable the aggregation of complementary information, leveraging the strengths of various measurement techniques to enhance robustness and accuracy.Technology is only effective with users; thus, beyond developing methods, fostering adoption among professionals and citizens is essential. Alongside technical advancements, researchers have explored psychological and social factors influencing the acceptance and trust of AI systems, particularly in healthcare and education. Trust has proven pivotal for AI adoption, with studies investigating how to build it and what system attributes ensure trustworthiness (Li et al., 2024). Key trust factors include explainability, transparency in processes and data usage, and the credibility of the institutions behind AI development.This Research Topic explores novel theories, methodologies, and applications of Emotion AI in healthcare and education. The published works address technical aspects, models, and AI acceptance and literacy. Burgess et al. (2023) evaluated automated facial coding software for parent-infant interactions across five studies with fathers and mothers. Automated detection rates were low (~25%) compared to manual coding in naturalistic settings but strongly correlated with manual assessments, particularly for positive expressions, when successful. Key challenges included poor lighting, facial occlusion, and rapid movements, highlighting the need for greater robustness in real-world conditions. Despite these limitations, the study demonstrated the potential of automated systems for analyzing authentic emotional expressions in parent-child interactions. 2023) introduced an innovative semi-supervised learning approach for stress monitoring. Using physiological data from 14 participants across five experiments, they achieved 77% accuracy with label propagation and 76% with deep autoencoders despite utilizing only 17% labeled data. Their method matched the performance of fully supervised approaches while substantially reducing annotation requirements, offering a practical solution for continuous stress monitoring in real-world healthcare applications. Žvanut and Mihelič (2024) identified four distinct attitudes among older adults toward domestic social robots: Cautious Optimists, Skeptical Traditionalists, Positive Optimists, and Technophiles. Through interviews with 24 participants, they highlighted the influence of factors like technology familiarity, privacy concerns, and perceived utility on AI acceptance. Their findings offer valuable insights for designing emotionally intelligent robotic assistants tailored to diverse user needs and concerns. Shen and Cui (2024) investigated the link between psychological needs satisfaction and AI literacy in 445 university students. Their findings revealed that technical and teacher support positively impacted students' autonomy and competence, subsequently improving AI literacy. Notably, satisfying psychological needs proved more critical than direct support in enhancing AI literacy. These insights offer valuable guidance for designing AI-enhanced educational environments that foster better learning and engagement. Gong et al. (2024) examined patients' trust in AI-powered pharmacy intravenous admixture services across five studies. They found that patients generally trusted AI PIVAS less than human services, primarily due to a limited subjective understanding of AI systems. However, informed consent significantly improved trust by enhancing patients' understanding. This study underscores the critical role of transparent communication and psychological factors in adopting AI in healthcare.The articles in this Research Topic advance methods for analyzing real-world datasets and explore how Emotion AI can be effectively integrated into healthcare and education, addressing challenges related to trust, privacy, and user acceptance. While Emotion AI shows promise, its use in these fields raises technical and ethical concerns, including data privacy, surveillance, and potential misuse of personal information. Clinical applications are further constrained by small sample sizes, lack of control groups, limited real-world testing, and methodological variability, which hinder reproducibility and reliability (Pepa et al., 2023). These studies tackle these challenges by developing novel model-training approaches for limited and noisy labeled data and identifying factors influencing AI acceptance and trust.Future research should prioritize enhancing the robustness of emotion recognition in naturalistic settings, developing efficient learning methods to reduce dependence on labeled data, and addressing ethical considerations to support user acceptance of AI. Emphasis on cross-cultural validation and long-term evaluation in real-world applications is crucial. Recent generative AI (GenAI) foundation models, such as GPT-4, offer significant potential for advancing Emotion AI due to their versatility (Cheng et al., 2023). GenAI has already shown promise in recognizing emotional indicators (Elyoseph et al., 2024) and could help alleviate data scarcity challenges that hinder specialized model development. Additionally, there is growing interest in the emotional analysis of groups and crowds, broadening the field's scope (Veltmeijer et al., 2023;Li et al. 2024).

Graphs have been widely applied in modeling the relationships and structures in real-world applications. Graph construction is the most critical part in these models, while how to construct an effective graph is still an open problem. In this chapter, we propose a novel approach to graph construction based on two observations. First, by virtue of recent advances in low-rank subspace recovery, the similarity between every two samples evaluated in the low-rank code space is more robust than that in the sample space. Second, a sparse and balanced graph can greatly increase the performance of learning tasks, such as label propagation in graph based semi-supervised learning. The k-NN sparsification can provide fast solutions to constructing unbalanced sparse graphs, and b-matching constraint is a necessary route for generating balanced graphs. These observations motivate us to jointly learn the low-rank codes and balanced (or unbalanced) graph simultaneously. In particular, two non-convex models are built by incorporating k-NN constraint and b-matching constraint into the low-rank representation model, respectively. We design a majorization-minimization augmented Lagrange multiplier (MM-ALM) algorithm to solve the proposed models. Extensive experimental results on four image databases demonstrate the superiority of our graphs over several state-of-the-art graphs in data clustering, transductive and inductive semi-supervised learning.

Speaker attribution is required in many real-world applications, such as\nmeeting transcription, where speaker identity is assigned to each utterance\naccording to speaker voice profiles. In this paper, we propose to solve the\nspeaker attribution problem by using graph-based semi-supervised learning\nmethods. A graph of speech segments is built for each session, on which\nsegments from voice profiles are represented by labeled nodes while segments\nfrom test utterances are unlabeled nodes. The weight of edges between nodes is\nevaluated by the similarities between the pretrained speaker embeddings of\nspeech segments. Speaker attribution then becomes a semi-supervised learning\nproblem on graphs, on which two graph-based methods are applied: label\npropagation (LP) and graph neural networks (GNNs). The proposed approaches are\nable to utilize the structural information of the graph to improve speaker\nattribution performance. Experimental results on real meeting data show that\nthe graph based approaches reduce speaker attribution error by up to 68%\ncompared to a baseline speaker identification approach that processes each\nutterance independently.\n

Canonical Correlation Analysis of Task Related Components as a noise-resistant method in Brain-Computer Interface Speller Systems based on Steady-State Visual Evoked Potential

Semi-supervised learning and continuous learning are fundamental paradigms for human-level intelligence. To deal with real-world problems where labels are rarely given and the opportunity to access the same data is limited, it is necessary to apply these two paradigms in a joined fashion. In this paper, we propose Label Propagation Adaptive Resonance Theory (LPART) for semi-supervised continuous learning. LPART uses an online label propagation mechanism to perform classification and gradually improves its accuracy as the observed data accumulates. We evaluated the proposed model on visual (MNIST, SVHN, CIFAR-10) and audio (NSynth) datasets by adjusting the ratio of the labeled and unlabeled data. The accuracies are much higher when both labeled and unlabeled data are used, demonstrating the significant advantage of LPART in environments where the data labels are scarce.

The current damage is the most stubborn and difficult fault of high-power motor bearings because its vibration characteristics are easily confused with those of ordinary bearing mechanical faults. If it is discriminated as an ordinary mechanical fault without electrical insulation protection, the current damage of bearing shafts will still repeatedly appear. Aiming at the problem that it is difficult to identify the bearing current damage fault under variable working conditions, a bearing shaft current damage identification method based on multiscale feature label propagation and manifold metric transfer (MFLP-MMT) is proposed. Firstly, the multiscale sub-band signal is obtained by wavelet packet decomposition, and the multiscale sub-band fuzzy entropy is obtained by calculating its fuzzy entropy. Then, according to the extracted features, a neighbor graph is constructed on the source domain of the known fault label to obtain the pseudo label of the target domain sample, and the source domain label information is gradually diffused by way of the graph label propagation. The multiscale sub-band fuzzy entropy of the sample is mapped to the low-dimensional manifold space by locality preserving projections (LPP), and the source domain samples close to the target domain are given higher weights by cross-domain density ratio estimation to solve the problem of domain offset. Combined with the label samples of the target domain in label propagation, the manifold distance metric is learned to minimize the intra-class distance and maximize the inter-class distance in the domain and eliminate the overlapping phenomenon in the domain. By increasing the range of label propagation after each iteration, the label propagation error of the leading graph is gradually reduced, and unsupervised metric transfer learning is realized. The experimental results show that the new method is superior to the semi-supervised transfer learning method in fault identification ability; the highest fault identification accuracy can reach 100% and it has a good robustness.