Label Constraints Research Articles

Dual semi-supervised hypergraph regular multi-view NMF with anchor graph embedding

Graph regularized nonnegative matrix factorization (GNMF) has been widely used in multi-view clustering tasks due to its good clustering properties. However, it uses a simple graph to describe the complex data relationship of multiple views and tries to obtain a consistent low-dimensional representation, which undoubtedly brings challenges to its clustering performance. In addition, clustering a large amount of high-dimensional data from multiple views undoubtedly faces a huge computational burden. In order to effectively improve the performance and efficiency of GNMF based multi-view clustering algorithm, this paper proposes a dual semi-supervised hypergraph regular multi-view clustering method with anchor graph embedding (DSSHMNMFAE). Specifically, DSSHMNMFAE develops a new anchor selection method to generate anchors and the anchor bipartite graph is constructed to embed the matrix factorization process. DSSHMNMFAE constructs a hypergraph to effectively learn the high-order relationship between data from multiple views. In order to perform semi-supervised learning more efficiently, DSSHMNMFAE integrates pairwise constraint information and label constraint information into the clustering process as dual label information. In addition, DSSHMNMFAE considers the learning of both consistency information and complementarity information, and adopts adaptive measures to distinguish the contributions of different views. We use the alternating iterative algorithm to optimize the objective function of DSSHMNMFAE. The experimental results on eight real datasets show that the performance of DSSHMNMFAE is comparable to other algorithms.

Multimodal Emotion-Cause Pair Extraction with Holistic Interaction and Label Constraint

Multimodal Emotion-Cause Pair Extraction with Holistic Interaction and Label Constraint

Convolutional neural network application for supply–demand matching in Zhuang ethnic clothing image classification

This study aims to design a classification technique suitable for Zhuang ethnic clothing images by integrating the concept of supply–demand matching and convolutional neural networks. Firstly, addressing the complex structure and unique visual style of Zhuang ethnic clothing, this study proposes an image resolution model based on supply–demand matching and convolutional networks. By integrating visual style and label constraints, this model accurately extracts local features. Secondly, the model’s effectiveness and resolution performance are analyzed through various performance metrics in experiments. The results indicate a significant improvement in detection accuracy at different annotation points. The model outperforms other comparative methods in pixel accuracy (90.5%), average precision (83.7%), average recall (80.1%), and average F1 score (81.2%). Next, this study introduces a clothing image classification algorithm based on key points and channel attention. Through key point detection and channel attention mechanisms, image features are optimized, enabling accurate classification and attribute prediction of Zhuang ethnic clothing. Experimental results demonstrate a notable enhancement in category classification and attribute prediction, with classification accuracy and recall exceeding 90% in top-k tasks, showcasing outstanding performance. In conclusion, this study provides innovative approaches and effective solutions for deep learning classification of Zhuang ethnic clothing images.

I/O Efficient Label-Constrained Reachability Queries in Large Graphs

Computing the reachability between two vertices in a graph is a fundamental problem in graph data analysis. Most of the existing works assume that the edges in the graph have no labels, but in many real application scenarios, edges naturally come with edge-labels, and label constraints may be placed on the edges appearing on a valid path between two query vertices. Therefore, we study the label-constrained reachability (LCR) queries in this paper, where we are given a source vertex s , a target vertex t , a label set Δ, and the goal is to check whether there exists any path from s to t such that all the labels of edges on the path belong to Δ. A plethora of methods have been proposed in the literature to support the LCR queries. All these methods take the assumption that the graph is resident in the main memory of a machine. Nevertheless, the graphs in many real application scenarios are generally big and may not reside in memory. In these cases, existing methods suffer from serious scalability problem, i.e., result in huge I/O costs. Motivated by this, in this paper, we study the I/O efficient LCR query problem and aim to efficiently answer the LCR queries when the graph cannot fit in the main memory. To achieve this goal, we propose a reduction-based indexing approach. We introduce two elegant graph reduction operators which aims to reduce the size of the graph loaded in memory while preserving the LCR information among the remaining vertices. With these two operators, we devise an index named LCR-Index and propose algorithms to adaptively construct the index based on the available memory. Equipped with LCR-Index, we can answer a LCR query by only scanning the LCR-Index sequentially. Experiments demonstrate our query processing algorithm can handle graphs with billions of edges.

Diagnosis-Guided Deep Subspace Clustering Association Study for Pathogenetic Markers Identification of Alzheimer's Disease Based on Comparative Atlases.

The roles of brain region activities and genotypic functions in the pathogenesis of Alzheimer's disease (AD) remain unclear. Meanwhile, current imaging genetics methods are difficult to identify potential pathogenetic markers by correlation analysis between brain network and genetic variation. To discover disease-related brain connectome from the specific brain structure and the fine-grained level, based on the Automated Anatomical Labeling (AAL) and human Brainnetome atlases, the functional brain network is first constructed for each subject. Specifically, the upper triangle elements of the functional connectivity matrix are extracted as connectivity features. The clustering coefficient and the average weighted node degree are developed to assess the significance of every brain area. Since the constructed brain network and genetic data are characterized by non-linearity, high-dimensionality, and few subjects, the deep subspace clustering algorithm is proposed to reconstruct the original data. Our multilayer neural network helps capture the non-linear manifolds, and subspace clustering learns pairwise affinities between samples. Moreover, most approaches in neuroimaging genetics are unsupervised learning, neglecting the diagnostic information related to diseases. We presented a label constraint with diagnostic status to instruct the imaging genetics correlation analysis. To this end, a diagnosis-guided deep subspace clustering association (DDSCA) method is developed to discover brain connectome and risk genetic factors by integrating genotypes with functional network phenotypes. Extensive experiments prove that DDSCA achieves superior performance to most association methods and effectively selects disease-relevant genetic markers and brain connectome at the coarse-grained and fine-grained levels.

Transfer Learning-Based Hyperspectral Image Classification Using Residual Dense Connection Networks.

The extraction of effective classification features from high-dimensional hyperspectral images, impeded by the scarcity of labeled samples and uneven sample distribution, represents a formidable challenge within hyperspectral image classification. Traditional few-shot learning methods confront the dual dilemma of limited annotated samples and the necessity for deeper, more effective features from complex hyperspectral data, often resulting in suboptimal outcomes. The prohibitive cost of sample annotation further exacerbates the challenge, making it difficult to rely on a scant number of annotated samples for effective feature extraction. Prevailing high-accuracy algorithms require abundant annotated samples and falter in deriving deep, discriminative features from limited data, compromising classification performance for complex substances. This paper advocates for an integration of advanced spectral-spatial feature extraction with meta-transfer learning to address the classification of hyperspectral signals amidst insufficient labeled samples. Initially trained on a source domain dataset with ample labels, the model undergoes transference to a target domain with minimal samples, utilizing dense connection blocks and tree-dimensional convolutional residual connections to enhance feature extraction and maximize spatial and spectral information retrieval. This approach, validated on three diverse hyperspectral datasets-IP, UP, and Salinas-significantly surpasses existing classification algorithms and small-sample techniques in accuracy, demonstrating its applicability to high-dimensional signal classification under label constraints.

Spatial-Logic-Aware Weakly Supervised Learning for Flood Mapping on Earth Imagery

Flood mapping on Earth imagery is crucial for disaster management, but its efficacy is hampered by the lack of high-quality training labels. Given high-resolution Earth imagery with coarse and noisy training labels, a base deep neural network model, and a spatial knowledge base with label constraints, our problem is to infer the true high-resolution labels while training neural network parameters. Traditional methods are largely based on specific physical properties and thus fall short of capturing the rich domain constraints expressed by symbolic logic. Neural-symbolic models can capture rich domain knowledge, but existing methods do not address the unique spatial challenges inherent in flood mapping on high-resolution imagery. To fill this gap, we propose a spatial-logic-aware weakly supervised learning framework. Our framework integrates symbolic spatial logic inference into probabilistic learning in a weakly supervised setting. To reduce the time costs of logic inference on vast high-resolution pixels, we propose a multi-resolution spatial reasoning algorithm to infer true labels while training neural network parameters. Evaluations of real-world flood datasets show that our model outperforms several baselines in prediction accuracy. The code is available at https://github.com/spatialdatasciencegroup/SLWSL.

Kernel-Based Sparse Representation Learning With Global and Local Low-Rank Label Constraint

Kernel-Based Sparse Representation Learning With Global and Local Low-Rank Label Constraint

RETRACTED: DL-SCA: An deep learning based approach for intra-class CutMix data augmentation

CutMix data augmentation can provide a large amount of augmented data for DL-SCA (deep learning side channel attacks) by generating new power traces. However, traces generated by CutMix may lose dependency with the new label, which may reduce the accuracy of the training model. In light of this, we propose an improved intra-class CutMix data augmentation method. Firstly, the original power traces are classified by the label. Then, the original power traces are selected by the same label constraint to generate new power traces according to CutMix, which can ensure the dependency between the generated trace and its label. Furthermore, to maintain balance among different classified datasets, the traces are generated sequentially according to distinct labels. Finally, based on the augmented power traces, the MLP (Multilayer Perceptron) and CNN (Convolutional Neural Network) models can be constructed and trained to recover the key of AES. In order to verify the effectiveness of the proposed method, we conducted experimental evaluations using the MLP and CNN models based on DPA-contest v4 dataset and ASCAD dataset. The test results show that the generated traces based on the intra-class CutMix method can be very similar to the original power traces, and the MLP and CNN models can be effectively trained based on the generated traces to recover the key of AES. Compared with existing data augmentation methods, the proposed method can complete the key recovery with faster convergence and fewer power traces.

Characterizing Time Spent in Video Object Tracking Annotation Tasks: A Study of Task Complexity in Vehicle Tracking

Video object tracking annotation tasks are a form of complex data labeling that is inherently tedious and time-consuming. Prior studies of these tasks focus primarily on quality of the provided data, leaving much to be learned about how the data was generated and the factors that influenced how it was generated. In this paper, we take steps toward this goal by examining how human annotators spend their time in the context of a video object tracking annotation task. We situate our study in the context of a standard vehicle tracking task with bounding box annotation. Within this setting, we study the role of task complexity by controlling two dimensions of task design -- label constraint and label granularity -- in conjunction with worker experience. Using telemetry and survey data collected from 40 full-time data annotators at a large technology corporation, we find that each dimension of task complexity uniquely affects how annotators spend their time not only during the task, but also before it begins. Furthermore, we find significant misalignment in how time-use was observed and how time-use was self-reported. We conclude by discussing the implications of our findings in the context of video object tracking and the need to better understand how productivity can be defined in data annotation.

Answering reachability queries with ordered label constraints over labeled graphs

Answering reachability queries with ordered label constraints over labeled graphs

A Hierarchy-driven Multi-label Network with Label Constraints for Post-operative Complication Prediction of Lung Cancer.

Lung cancer is one of the most dangerous cancers all over the world. Surgical resection remains the only potentially curative option for patients with lung cancer. However, this invasive treatment often causes various complications, which seriously endanger patient health. In this study, we proposed a novel multi-label network, namely a hierarchy-driven multi-label network with label constraints (HDMN-LC), to predict the risk of complications of lung cancer patients. In this method, we first divided all complications into pulmonary and cardiovascular complication groups and employed the hierarchical cluster algorithm to analyze the hierarchies between these complications. After that, we employed the hierarchies to drive the network architecture design so that related complications could share more hidden features. And then, we combined all complications and employed an auxiliary task to predict whether any complications would occur to impose the bottom layer to learn general features. Finally, we proposed a regularization term to constrain the relationship between specific and combined complication labels to improve performance. We conducted extensive experiments on real clinical data of 593 patients. Experimental results indicate that the proposed method outperforms the single-label, multi-label baseline methods, with an average AUC value of 0.653. And the results also prove the effectiveness of hierarchy-driven network architecture and label constraints. We conclude that the proposed method can predict complications for lung cancer patients more effectively than the baseline methods.Clinical relevance-This study presents a novel multi-label network that can more accurately predict the risk of specific postoperative complications for lung cancer patients. The method can help clinicians identify high-risk patients more accurately and timely so that interventions can be implemented in advance to ensure patient safety.

Multi-view clustering via label-embedded regularized NMF with dual-graph constraints

Nonnegative matrix factorization (NMF) methods have achieved remarkable performances in multi-view clustering due to their effectiveness and efficiency. To better obtain a low-dimensional common representation, the limited labels and the geometric structure of the multi-view data should be fully utilized in clustering. In this work, we introduce a novel multi-view learning approach, dubbed label-embedded regularized NMF with dual-graph constraints (LeNMF-DC), for clustering. Our proposed LeNMF-DC approach mainly utilizes matrix factorization to obtain a low-dimensional common representation of the multi-view data, in which the prior knowledge hidden in data can be fully explored. Specifically, we construct three graph regularization terms to preserve the manifold structure in the data, feature and label space, respectively. Moreover, we take advantage of the labels of the labeled samples without additional parameters. In addition, we develop an alternate iterative optimization scheme to solve the model of LeNMF-DC and then show its convergence rate. Compared with traditional multi-view clustering approaches, the labels of unlabeled samples in our proposed LeNMF-DC approach are assigned by the label constraint matrix rather than the clustering algorithm, and thus it avoids performance loss during the clustering. Experimental results on four benchmark datasets manifest that our LeNMF-DC approach can achieve superior performances than several state-of-the-art approaches in multi-view clustering.

Spectral clustering with robust self-learning constraints

Spectral clustering is a leading unsupervised classification algorithm widely used to capture complex clusters in unlabeled data. Additional prior information can further enhance the quality of spectral clustering results to satisfy users' expectations. However, it is challenging for users to find the prior information under unsupervised scenes. To get rid of the deficiency, we propose a spectral clustering model with robust self-learning constraints. In this model, we first extend the optimization problem of spectral clustering by seeing label constraints as variables to learn the constraints and the clustering result simultaneously. Furthermore, we add a robust term to the proposed model so that we can learn multiple groups of label constraints to guide the clustering process and find a robust self-constrained spectral clustering result. The robust term can reduce the impact of uncertainty in the quality of a single set of label constraints on the performance of the proposed model. An iterative strategy with update formulas for variables is proposed to solve the self-constrained spectral clustering problem. We provide the theoretical analysis to explain the importance of the learned constraints in spectral clustering. Furthermore, we analyze the convergence of our optimization scheme. Finally, we have done many experiments on benchmark data sets to illustrate the effectiveness of the proposed algorithm.

Identifying Modality-Consistent and Modality-Specific Features via Label-Guided Multi-Task Sparse Canonical Correlation Analysis for Neuroimaging Genetics.

Brain imaging genetics provides the foundation for further revealing brain disorder, which combines genetic variation with brain structure or functions. Recently, sparse canonical correlation analysis (SCCA) and multimodality analysis have been widely utilized for imaging genetics. However, SCCA is an unsupervised learning method which ignores the diagnostic information related to the disease. Traditional multimodality analysis cannot distinguish the consistent and specific information from different neuroimaging that are correlated to the genotypic variances. In this paper, we propose the Label-Guided Multi-task Sparse Canonical Correlation Analysis (LGMTSCCA) method to identify the informative features from the single nucleotide polymorphisms (SNPs) and brain regions related to the pathogenesis of Alzheimer's disease (AD). Specifically, LGMTSCCA uses label constraint via inducing diagnostic information to guide the imaging genetic correlation learning. Considering multi-modal imaging genetic correlations, we use the weight decomposition strategy to calculate the correlation weights in consistency and specificity with different parameters. We evaluate the effectiveness of the LGMTSCCA on synthetic and real data sets. The experimental results show LGMTSCCA can achieve superior performances than the existing methods, which has more flexible ability for identifying modality-consistent and modality-specific features.

Class Imbalanced Medical Image Classification Based on Semi-Supervised Federated Learning

In recent years, the application of federated learning to medical image classification has received much attention and achieved some results in the study of semi-supervised problems, but there are problems such as the lack of thorough study of labeled data, and serious model degradation in the case of small batches in the face of the data category imbalance problem. In this paper, we propose a federated learning method using a combination of regularization constraints and pseudo-label construction, where the federated learning framework consists of a central server and local clients containing only unlabeled data, and labeled data are passed from the central server to each local client to take part in semi-supervised training. We first extracted the class imbalance factors from the labeled data to participate in the training to achieve label constraints, and secondly fused the labeled data with the unlabeled data at the local client to construct augmented samples, looped through to generate pseudo-labels. The purpose of combining these two methods is to select fewer classes with higher probability, thus providing an effective solution to the class imbalance problem and improving the sensitivity of the network to unlabeled data. We experimentally validated our method on a publicly available medical image classification data set consisting of 10,015 images with small batches of data. Our method improved the AUC by 7.35% and the average class sensitivity by 1.34% compared to the state-of-the-art methods, which indicates that our method maintains a strong learning capability even with an unbalanced data set with fewer batches of trained models.

Analyzing drop coalescence in microfluidic devices with a deep learning generative model.

Predicting drop coalescence based on process parameters is crucial for experimental design in chemical engineering. However, predictive models can suffer from the lack of training data and more importantly, the label imbalance problem. In this study, we propose the use of deep learning generative models to tackle this bottleneck by training the predictive models using generated synthetic data. A novel generative model, named double space conditional variational autoencoder (DSCVAE) is developed for labelled tabular data. By introducing label constraints in both the latent and the original space, DSCVAE is capable of generating consistent and realistic samples compared to the standard conditional variational autoencoder (CVAE). Two predictive models, namely random forest and gradient boosting classifiers, are enhanced on synthetic data and their performances are evaluated based on real experimental data. Numerical results show that a considerable improvement in prediction accuracy can be achieved by using synthetic data and the proposed DSCVAE clearly outperforms the standard CVAE. This research clearly provides more insights into handling imbalanced data for classification problems, especially in chemical engineering.

Discriminative Nonnegative Tucker Decomposition for Tensor Data Representation

Nonnegative Tucker decomposition (NTD) is an unsupervised method and has been extended in many applied fields. However, NTD does not make use of the label information of sample data, even though such label information is available. To remedy the defect, in this paper, we propose a label constraint NTD method, namely Discriminative NTD (DNTD), which considers a fraction of the label information of the sample data as a discriminative constraint. Differing from other label-based methods, the proposed method enforces the sample data, with the same label to be aligned on the same axis or line. Combining the NTD and the label-discriminative constraint term, DNTD can not only extract the part-based representation of the data tensor but also boost the discriminative ability of the NTD. An iterative updating algorithm is provided to solve the objective function of DNTD. Finally, the proposed DNTD method is applied to image clustering. Experimental results on ORL, COIL20, Yale datasets show the clustering accuracy of DNTD is improved by 8.47–32.17% and the normalized mutual information is improved by 10.43–29.64% compared with the state-of-the-art approaches.

Deep Realistic Facial Editing via Label-restricted Mask Disentanglement.

With the rapid development of GAN (generative adversarial network), recent years have witnessed an increasing number of tasks on reference-guided facial attributes transfer. Most state-of-the-art methods consist of facial information extraction, latent space disentanglement, and target attribute manipulation. However, they either adopt reference-guided translation methods for manipulation or monolithic modules for diverse attribute exchange, which cannot accurately disentangle the exact facial attributes with specific styles from the reference image. In this paper, we propose a deep realistic facial editing method (termed LMGAN) based on target region focusing and dual label constraint. The proposed method, manipulating target attributes by latent space exchange, consists of subnetworks for every individual attribute. Each subnetwork exerts label-restrictions on both the target attributes exchanging stage and the training process aimed at optimizing generative quality and reference-style correlation. Our method performs greatly on disentangled representation and transferring the target attribute's style accurately. A global discriminator is introduced to combine the generated editing regional image with other nonediting areas of the source image. Both qualitative and quantitative results on the CelebA dataset verify the ability of the proposed LMGAN.

Egocentric video co-summarization using transfer learning and refined random walk on a constrained graph

In this paper, we address the problem of egocentric video co-summarization. We show how a shot level accurate summary can be obtained in a time-efficient manner using random walk on a constrained graph in transfer learned feature space with label refinement. While applying transfer learning, we propose a new loss function capturing egocentric characteristics in a pre-trained ResNet on the set of auxiliary egocentric videos. Transfer learning is used to generate i) an improved feature space and ii) a set of labels to be used as seeds for the test egocentric video. A complete weighted graph is created for a test video in the new transfer learned feature space with shots as the vertices. We derive two types of cluster label constraints in form of Must-Link (ML) and Cannot-link (CL) based on the similarity of the shots. ML constraints are used to prune the complete graph which is shown to result in substantial computational advantage, especially, for the long duration videos. We derive expressions for the number of vertices and edges for the ML-constrained graph and show that this graph remains connected. Random walk is applied to obtain labels of the unmarked shots in this new graph. CL constraints are applied to refine the cluster labels. Finally, shots closest to individual cluster centres are used to build the summary. Experiments on the short duration videos as in CoSum and TVSum datasets and long duration videos as in ADL and EPIC-Kitchens datasets clearly demonstrate the advantage of our solution over several state-of-the-art methods.