Multi-label Classification Task Research Articles

Sequence Generation Model Integrating Domain Ontology for Mathematical question tagging

In online learning systems, tagging knowledge points for questions is a fundamental task. Automatic tagging technology uses intelligent algorithms to automatically tag knowledge points for questions to reduce manpower and time costs. However, the current knowledge point tagging technology cannot satisfy the situation that mathematics questions often involve a variable number of knowledge points, lacks the consideration of the characteristics of the mathematics field, and ignores the internal connection between knowledge points. To address the above issues, we propose a Sequence Generation Model Integrating Domain Ontology for Mathematical question tagging (SOMPT). SOMPT performs data augmentation for text and then obtains intermediate text based on domain ontology replacement to facilitate deep learning model to understand mathematical question text. SOMPT is able to obtain dynamic word vector embedding to optimize the textual representation for math questions. What’s more, our model can capture the relationship between tags to generate knowledge points more accurately in the way of sequence generation. The comparative experimental results show that our proposed model has an excellent tagging ability for mathematical questions. Moreover, the sequence generation module in SOMPT can be applied on other multi-label classification tasks and be on par with the state-of-the-art performance 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.

Improving passive acoustic target detection using machine learning classifiers

The ocean covers 70% of the Earth surface area, yet over 80% of it remains unexplored despite the advances in underwater acoustics and oceanography. Ocean exploration is critical for accurate climate model development, renewable energy applications, and in understanding the marine habitat. Further exploration necessitates improvements in underwater navigation with Autonomous Underwater Vehicles (AUVs). Utilizing acoustic landmarks can enhance AUV localization performance [Fula et al., Oceans IEEE/MTS (2018)]. Passive markers called Acoustic Identification (AID) Tags have unique and identifiable acoustic reflection signatures designed to function as landmarks [Satish et al., JASA 149 (2021)]. These targets can be detected by Match Filtering returns with template signals. Match Filtering performance is limited in the presence of strong interfering signals, and with changes in sound speeds that alters the temporal structure of these signatures. The application of a Machine Learning classifiers for detecting AID tag signatures can improve the localization performance. Through implementation of Logistic Regression, Deep Neural Networks, and Convolutional Neural Networks, the generalizability and superiority of these models is demonstrated. We report high accuracies (>90 %) in a multilabel (8 classes) classification task with signals with low SNR (–6 dB) and strong interference (+12 dB).

Attention-Augmented Memory Network for Image Multi-Label Classification

The purpose of image multi-label classification is to predict all the object categories presented in an image. Some recent works exploit graph convolution network to capture the correlation between labels. Although promising results have been reported, these methods cannot learn salient object features in the images and ignore the correlation between channel feature maps. In addition, the current researches only learn the feature information within individual input image, but fail to mine the contextual information of various categories from the dataset to enhance the input feature representation. To address these issues, we propose an A ttention- A ugmented M emory N etwork ( AAMN ) model for the image multi-label classification task. Specifically, we first propose a novel categorical memory module to excavate the contextual information of various categories from the dataset to augment the current input feature. Secondly, we design a new channel-relation exploration module to capture the inter-channel relationship of features, so as to enhance the correlation between objects in the images. Thirdly, we develop a spatial-relation enhancement module to model second-order statistics of features and capture long-range dependencies between pixels in feature maps, so as to learn salient object features. Experimental results on standard benchmarks, including MS-COCO 2014, PASCAL VOC 2007, and VG-500, demonstrate the effectiveness and superiority of AAMN model, which outperforms current state-of-the-art methods.

Aligning Image Semantics and Label Concepts for Image Multi-Label Classification

Image multi-label classification task is mainly to correctly predict multiple object categories in the images. To capture the correlation between labels, graph convolution network based methods have to manually count the label co-occurrence probability from training data to construct a pre-defined graph as the input of graph network, which is inflexible and may degrade model generalizability. Moreover, most of the current methods cannot effectively align the learned salient object features with the label concepts, so that the predicted results of model may not be consistent with the image content. Therefore, how to learn the salient semantic features of images and capture the correlation between labels, and then effectively align them is one of the key to improve the performance of image multi-label classification task. To this end, we propose a novel image multi-label classification framework which aims to align I mage S emantics with L abel C oncepts ( ISLC ). Specifically, we propose a residual encoder to learn salient object features in the images, and exploit the self-attention layer in aligned decoder to automatically capture the correlation between labels. Then, we leverage the cross-attention layers in aligned decoder to align image semantic features with label concepts, so as to make the labels predicted by model more consistent with image content. Finally, the output features of the last layer of residual encoder and aligned decoder are fused to obtain the final output feature for classification. The proposed ISLC model achieves good performance on various prevalent multi-label image datasets such as MS-COCO 2014, PASCAL VOC 2007, VG-500, and NUS-WIDE with 87.2%, 96.9%, 39.4%, and 64.2%, respectively.

Deep Network Architectures as Feature Extractors for Multi-Label Classification of Remote Sensing Images

Data in the form of images are now generated at an unprecedented rate. A case in point is remote sensing images (RSI), now available in large-scale RSI archives, which have attracted a considerable amount of research on image classification within the remote sensing community. The basic task of single-target multi-class image classification considers the case where each image is assigned exactly one label from a predefined finite set of class labels. Recently, however, image annotations have become increasingly complex, with images labeled with several labels (instead of just one). In other words, the goal is to assign multiple semantic categories to an image, based on its high-level context. The corresponding machine learning tasks is called multi-label classification (MLC). The classification of RSI is currently predominantly addressed by deep neural network (DNN) approaches, especially convolutional neural networks (CNNs), which can be utilized as feature extractors as well as end-to-end methods. After only considering single-target classification for a long period, DNNs have recently emerged that address the task of MLC. On the other hand, trees and tree ensembles for MLC have a long tradition and are the best-performing class of MLC methods, but need predefined feature representations to operate on. In this work, we explore different strategies for model training based on the transfer learning paradigm, where we utilize different families of (pre-trained) CNN architectures, such as VGG, EfficientNet, and ResNet. The architectures are trained in an end-to-end manner and used in two different modes of operation, namely, as standalone models that directly perform the MLC task, and as feature extractors. In the latter case, the learned representations are used with tree ensemble methods for MLC, such as random forests and extremely randomized trees. We conduct an extensive experimental analysis of methods over several publicly available RSI datasets and evaluate their effectiveness in terms of standard MLC measures. Of these, ranking-based evaluation measures are most relevant, especially ranking loss. The results show that, for addressing the RSI-MLC task, it is favorable to use lightweight network architectures, such as EfficientNet-B2, which is the best performing end-to-end approach, as well as a feature extractor. Furthermore, in the datasets with a limited number of images, using traditional tree ensembles for MLC can yield better performance compared to end-to-end deep approaches.

Double Attention Based on Graph Attention Network for Image Multi-Label Classification

The task of image multi-label classification is to accurately recognize multiple objects in an input image. Most of the recent works need to leverage the label co-occurrence matrix counted from training data to construct the graph structure, which are inflexible and may degrade model generalizability. In addition, these methods fail to capture the semantic correlation between the channel feature maps to further improve model performance. To address these issues, we propose DA-GAT (a D ouble A ttention framework based on the G raph A ttention ne T work) to effectively learn the correlation between labels from training data. First, we devise a new channel attention mechanism to enhance the semantic correlation between channel feature maps, so as to implicitly capture the correlation between labels. Second, we propose a new label attention mechanism to avoid the adverse impact of a manually constructed label co-occurrence matrix. It only needs to leverage the label embedding as the input of network, then automatically constructs the label relation matrix to explicitly establish the correlation between labels. Finally, we effectively fuse the output of these two attention mechanisms to further improve model performance. Extensive experiments are conducted on three public multi-label classification benchmarks. Our DA-GAT model achieves mean average precision of 87.1%, 96.6%, and 64.3% on MS-COCO 2014, PASCAL VOC 2007, and NUS-WIDE, respectively, and obviously outperforms other existing state-of-the-art methods. In addition, visual analysis experiments demonstrate that each attention mechanism can capture the correlation between labels well and significantly promote the model performance.

IMPROVING SELF-SUPERVISED LEARNING FOR MULTI-LABEL CLASSIFICATION USING MIX-BASED AUGMENTATIONS

Self-supervised learning is an active area of research that has had great advances recently. It is concerned with overcoming the bottleneck of any supervised deep learning framework that relies on hand-crafted labels to achieve good results. Several state-of-the-art self-supervised algorithms have been proposed recently, where most of these methods were designed to learn from ImageNet. Because ImageNet is an object-centric dataset, little focus was given in the design of the pretext task to adapt to complex scene understanding tasks such as multi-label classification or object detection. In this work, we investigate the question of whether applying mix-based augmentations in the self-supervised pretraining would lead to better transferability to the complex downstream task of multi-label classification. SimSiam, a non-contrastive self-supervised algorithm, is used for pretraining along with three proposed variations of mix-based augmentations. The task of multi-label classification on PascalVOC as a non-object centric dataset is selected for evaluation of the learned features. The SimSiam with the use of the UnMix augmentation technique achieved the best performance among all our experiments with higher Mean Average Precision (mAP) than the baseline by (+3.7). We conclude that lowering the mixing probability and using the new mixed image pairs as additions to the loss function is more efficient than replacing the original images completely. Our results confirm that more research that targets multi-object centric datasets is needed in the self-supervised domain. It also shows that applying mix-based augmentations to an already existing self-supervised algorithm improves downstream performance on multi-object centric datasets. Keywords: Self-Supervised Learning, Non-Contrastive Learning, UnMix, SimSiam, Mix-Based Augmentations DOI： https://doi.org/10.35741/issn.0258-2724.58.1.66

Combining the External Medical Knowledge Graph Embedding to Improve the Performance of Syndrome Differentiation Model.

The electronic medical records (EMRs) of traditional Chinese medicine (TCM) include a wealth of TCM knowledge and syndrome diagnosis information, which is crucial for improving the quality of TCM auxiliary decision-making. In practical diagnosis, one disease corresponds to one syndrome, posing considerable hurdles for the informatization of TCM. The purpose of this work was to create an end-to-end TCM diagnostic model, and the knowledge graph (KG) created in this article is used to improve the model's information and realize auxiliary decision-making for TCM disorders. We approached auxiliary decision-making for syndrome differentiation in this article as a multilabel classification task and presented a knowledge-based decision support model for syndrome differentiation (KDSD). Specifically, we created a KG based on TCM features (TCMKG), supplementing the textual representation of medical data with embedded information. Finally, we proposed fusing medical text with KG entity representation (F-MT-KER) to get prediction results using a linear output layer. After obtaining the vector representation of the medical record text using the BERT model, the vector representation of various KG embedded models can provide additional hidden information to a certain extent. Experimental results show that our method improves by 1% (P@1) on the syndrome differentiation auxiliary decision task compared to the baseline model BERT. The usage of EMRs can aid TCM development more efficiently. With the help of entity level representation, character level representation, and model fusion, the multilabel classification method based on the pretraining model and KG can better simulate the TCM syndrome differentiation of the complex cases.

Multi-Label Multimodal Emotion Recognition With Transformer-Based Fusion and Emotion-Level Representation Learning

Emotion recognition has been an active research area for a long time. Recently, multimodal emotion recognition from video data has grown in importance with the explosion of video content due to the emergence of short video social media platforms. Effectively incorporating information from multiple modalities in video data to learn robust multimodal representation for improving recognition model performance is still the primary challenge for researchers. In this context, transformer architectures have been widely used and have significantly improved multimodal deep learning and representation learning. Inspired by this, we propose a transformer-based fusion and representation learning method to fuse and enrich multimodal features from raw videos for the task of multi-label video emotion recognition. Specifically, our method takes raw video frames, audio signals, and text subtitles as inputs and passes information from these multiple modalities through a unified transformer architecture for learning a joint multimodal representation. Moreover, we use the label-level representation approach to deal with the multi-label classification task and enhance the model performance. We conduct experiments on two benchmark datasets: Interactive Emotional Dyadic Motion Capture (IEMOCAP) and Carnegie Mellon University Multimodal Opinion Sentiment and Emotion Intensity (CMU-MOSEI) to evaluate our proposed method. The experimental results demonstrate that the proposed method outperforms other strong baselines and existing approaches for multi-label video emotion recognition.

Multi-label classification of chest X-ray images with pre-trained vision Transformer model

目的 基于计算机的胸腔X线影像疾病检测和分类目前存在误诊率高，准确率低的问题。本文在视觉Transformer（vision Transformer，ViT）预训练模型的基础上，通过迁移学习方法，实现胸腔X线影像辅助诊断，提高诊断准确率和效率。方法 选用带有卷积神经网络（convolutional neural network，CNN）的ViT模型，其在超大规模自然图像数据集中进行了预训练；通过微调模型结构，使用预训练的ViT模型参数初始化主干网络，并迁移至胸腔X线影像数据集中再次训练，实现疾病多标签分类。结果 在IU X-Ray数据集中对ViT迁移学习前、后模型平均AUC（area under ROC curve）得分进行对比分析实验。结果表明，预训练ViT模型平均AUC得分为0.774，与不使用迁移学习相比提升了0.208。并针对模型结构和数据预处理进行了消融实验，对ViT中的注意力机制进行可视化，进一步验证了模型有效性。最后使用Chest X-Ray14和CheXpert数据集训练微调后的ViT模型，平均AUC得分为0.839和0.806，与对比方法相比分别有0.014～0.031的提升。结论 与其他方法相比，ViT模型胸腔X线影像的多标签分类精确度更高，且迁移学习可以在降低训练成本的同时提升ViT模型的分类性能和泛化性。消融实验与模型可视化表明，包含CNN结构的ViT模型能重点关注有意义的区域，高效获取胸腔X线影像的视觉特征。;Objective The chest X-ray-relevant screening and diagnostic method is essential for radiology nowadays. Most of chest X-ray images interpretation is still restricted by clinical experience and challenged for misdiagnose and missed diagnoses. To detect and identify one or more potential diseases in images automatically，it is beneficial for improving diagnostic efficiency and accuracy using computer-based technique. Compared to natural images，multiple lesions are challenged to be detected and distinguished accurately in a single image because abnormal areas have a small proportion and complex representations in chest X-ray images. Current convolutional neural network（CNN）based deep learning models have been widely used in the context of medical imaging. The structure of the CNN convolution kernel has sensitive to local detail information，and it is possible to extract richer image features. However，the convolution kernel cannot be used to get global information，and the features-extracted are restricted of redundant information like its relevance of background， muscles，and bones. The model’s performance in multi-label classification tasks are affected to a certain extent. At present，the vision Transformer（ViT）model has achieved its priorities in computer vision-related tasks. The ViT can be used to capture information simultaneously and effectively for multiple regions of the entire image. However，it is required to use large-scale dataset training to achieve good performance. Due to some factors like patient privacy and manual annotate costs，the size of the chest X-ray image data set has been limited. To reduce the model's dependence on data scale and improve the performance of multi-label classification，we develop the CNN-based ViT pre-training model in terms of the transfer learning method for diagnosis-assisted of chest X-ray image and multi-label classification. Method The CNN-based ViT model is pre-trained on a huge scale ground truth dataset，and it is used to obtain the initial parameters of the model. The model structure is fine-tuned according to the features of chest X-ray dataset. A 1×1 convolution layer is used to convert the chest X-ray images channels between 1 to 3. The number of output nodes of the linear layer in the classifier is balanced from 1 000 to the number of chest X-ray classification labels，and the Sigmoid is used as an activation function. The parameters of the backbone network are initialized in terms of the pre-trained ViT model parameters，and it is trained in the chest X-ray dataset after that to complete multi-label classification. The experiment is configured of Python3. 7 and PyTorch1. 8 to construct the model and RTX3090 GPU for training. Stochastic gradient descent（SGD）optimizer，binary cross-entropy（BCE）loss function，an initial learning rate of 1E-3，the cosine annealing learning rate decay are used. For training，each image is scaled to a size of 512×512 pixels，and a 224×224 pixels area and it is then cropped in random as the model input，and data augmentation is performed randomly by some of the flipping，perspective transformation， shearing，translation，zooming，and changing brightness. For testing，the chest X-ray image is scaled to 256×256 pixels and center crop a 224×224 area to input the trained model. Result The experiment is performed on the IU X-Ray，which is a small-scale chest X-ray dataset. This model is evaluated in quantitative using the average of area under ROC curve （AUC）scores across all classification labels. The results show that the average AUC score of the pre-trained ViT model is 0. 774. The accuracy and training efficiency of the non-pre-trained ViT model is dropped significantly. The average AUC score is reached to 0. 566 only，which is 0. 208 lower. In addition，the attention mechanism heat map is generated based on the ViT model，which can strengthen the interpretability of the model. A series of ablation experiments are carried out for data augmentation，model structure，and batch size design. The fine-tuned ViT model is trained on the Chest-Ray14 and CheXpert dataset as well. The average AUC score is reached to 0. 839 and 0. 806，which is optimized by 0. 014 and 0. 031. Conclusion A pre-trained ViT model is used for the multi-label classification of chest X-ray images via transfer learning. The experimental results illustrate that the ViT has its stronger multi-label classification performance in chest Xray images，and its attention mechanism is beneficial for lesions precision-focused like the interior of the chest cavity and the heart. Transfer learning is potential to improve the classification performance and model generalization of the ViT in small-scale datasets，and the training cost is reduced greatly. Ablation experiments demonstrate that the incorporated model of CNN and Transformer has its priority beyond single-structure model. Data enhancement and the batch size cutting can improve the performance of the model，but smaller scale of batch is still interlinked to longer training span. To improve the model's ability，we predict that future research direction can be focused on the extraction for complex disease and highlevel semantic information，such as their small lesions，disease location，and severity.

Advancing document-level event extraction: Integration across texts and reciprocal feedback.

The primary objective of document-level event extraction is to extract relevant event information from lengthy texts. However, many existing methods for document-level event extraction fail to fully incorporate the contextual information that spans across sentences. To overcome this limitation, the present study proposes a document-level event extraction model called Integration Across Texts and Reciprocal Feedback (IATRF). The proposed model constructs a heterogeneous graph and employs a graph convolutional network to enhance the connection between document and entity information. This approach facilitates the acquisition of semantic information enriched with document-level context. Additionally, a Transformer classifier is introduced to transform multiple event types into a multi-label classification task. To tackle the challenge of event argument recognition, this paper introduces the Reciprocal Feedback Argument Extraction strategy. Experimental results conducted on both our COSM dataset and the publicly available ChFinAnn dataset demonstrate that the proposed model outperforms previous methods in terms of F1 value, thus confirming its effectiveness. The IATRF model effectively solves the problems of long-distance document context-aware representation and cross-sentence argument dispersion.

Learning Dual Low-Rank Representation for Multi-Label Micro-Video Classification

Currently, with the rapid development of mobile Internet, micro-video has become a prevailing format of user-generated contents (UGCs) on various social media platforms. Several studies have been conducted towards to understanding high-level micro-video semantics, such as venue categorization, memorability, and popularity. However, these approaches supported tasks with only a single output, which exhibited limitations when attempting to use them to resolve tasks with multiple outputs, especially the multi-label micro-video classification. To tackle this problem, in this paper, we propose a dual multi-modal low-rank decomposition (DMLRD) method for multi-label micro-video classification tasks. To learn more comprehensive micro-video representations, we first learn the low-rank-regularized modality-specific and modality-shared components by considering the consistency and the complementarity among modalities simultaneously. Meanwhile, the less descriptive power of each modality aroused by inherent properties can be solved to a certain extent. To obtain unseen label representations, we next construct a sparsity-regularized multi-matrix normal estimation term to jointly encode the latent relationship structures among labels and dimensions. Experiments on two datasets demonstrate the effectiveness of our proposed method over the state-of-art methods.

A transformers-based approach on industrial disaster consequence identification from accident narratives

Industrial accidents are a major part of the more general technological disasters domain. These events vary from mild to severe and can affect millions of people and cause huge environmental and property damage. New technologies enable novel approaches and applications in the field of disaster management which help prevent, mitigate, and respond to such events. More specifically, transformers-based language models dominate natural language applications with outstanding state of the art performance. In this study an effort is being made to identify and evaluate the ability of transformers to extract and evaluate the consequences and effects of an industrial accident using natural language. The eMARS database is used for training data and a BERT model is used for fine tuning. The results on a multilabel classification task for consequence prediction from accident narratives are promising, achieving an overall weighted F1-score of 0.80.

A Novel Explainable CNN Model for Screening COVID-19 on X-ray Images

Due to the rapid propagation characteristic of the Coronavirus (COVID-19) disease, manual diagnostic methods cannot handle the large number of infected individuals to prevent the spread of infection. Despite, new automated diagnostic methods have been brought on board, particularly methods based on artificial intelligence using different medical data such as X-ray imaging. Thoracic imaging, for example, produces several image types that can be processed and analyzed by machine and deep learning methods. X-ray imaging materials widely exist in most hospitals and health institutes since they are affordable compared to other imaging machines. Through this paper, we propose a novel Convolutional Neural Network (CNN) model (COV2Net) that can detect COVID-19 virus by analyzing the X-ray images of suspected patients. This model is trained on a dataset containing thousands of X-ray images collected from different sources. The model was tested and evaluated on an independent dataset. In order to approve the performance of the proposed model, three CNN models namely Mobile-Net, Residential Energy Services Network (Res-Net), and Visual Geometry Group 16 (VGG-16) have been implemented using transfer learning technique. This experiment consists of a multi-label classification task based on X-ray images for normal patients, patients infected by COVID-19 virus and other patients infected with pneumonia. This proposed model is empowered with Gradient-weighted Class Activation Mapping (Grad-CAM) and Grad-Cam++ techniques for a visual explanation and methodology debugging goal. The finding results show that the proposed model COV2Net outperforms the state-of-the-art methods.

Attack Behavior Extraction Based on Heterogeneous Cyberthreat Intelligence and Graph Convolutional Networks

The continuous improvement of the cyber threat intelligence sharing mechanism provides new ideas to deal with Advanced Persistent Threats (APT). Extracting attack behaviors, i.e., Tactics, Techniques, Procedures (TTP) from Cyber Threat Intelligence (CTI) can facilitate APT actors’ profiling for an immediate response. However, it is difficult for traditional manual methods to analyze attack behaviors from cyber threat intelligence due to its heterogeneous nature. Based on the Adversarial Tactics, Techniques and Common Knowledge (ATT&CK) of threat behavior description, this paper proposes a threat behavioral knowledge extraction framework that integrates Heterogeneous Text Network (HTN) and Graph Convolutional Network (GCN) to solve this issue. It leverages the hierarchical correlation relationships of attack techniques and tactics in the ATT&CK to construct a text network of heterogeneous cyber threat intelligence. With the help of the Bidirectional Encoder Representation from Transformers (BERT) pretraining model to analyze the contextual semantics of cyber threat intelligence, the task of threat behavior identification is transformed into a text classification task, which automatically extracts attack behavior in CTI, then identifies the malware and advanced threat actors. The experimental results show that F1 achieve 94.86% and 92.15% for the multi-label classification tasks of tactics and techniques. Extend the experiment to verify the method’s effectiveness in identifying the malware and threat actors in APT attacks. The F1 for malware and advanced threat actors identification task reached 98.45% and 99.48%, which are better than the benchmark model in the experiment and achieve state of the art. The model can effectively model threat intelligence text data and acquire knowledge and experience migration by correlating implied features with a priori knowledge to compensate for insufficient sample data and improve the classification performance and recognition ability of threat behavior in text.

Research on multi-label user classification of social media based on ML-KNN algorithm

Several research studies have been conducted on multi-label classification algorithms for text and images, but few have been conducted on multi-label classification for users. Moreover, the existing multi-label user classification algorithm does not provide an effective representation of users, and it is difficult to use directly in social media scenarios. By analyzing complex social networks, this paper aims to achieve multi-label classification of users based on research in single-label classification.Considering the limitations of existing research, this paper proposes a user topic classification method based on heterogeneous networks as well as a user multi-label classification method based on community detection. The model is trained using the ML-KNN multi-label classification algorithm. In actual scenarios, the algorithm is more effective than existing multi-label classification methods when applied to multi-label classification tasks for social media users.According to the results of the analysis, the algorithm has a high level of accuracy in classifying different theme users into a variety of different scenarios using different theme users. Furthermore, this study contributes to the advancement of classification research by expanding its perspective.

Multi-label weak-label learning via semantic reconstruction and label correlations

In the multi-label classification task, an instance is simultaneously associated with multiple semantic labels. Due to the high complexity of the semantic space in practical applications, obtaining instances with full labels is difficult, leading to the weak-label problem. Existing methods focus on the low-rank and instance manifold regularization assumptions of the label matrix to recover the ground-truth label matrix but ignore the influence that the above assumptions may not hold due to the semantic noise caused by missing labels. To address the problem, this paper proposes a simple and effective method to recover the label space by reconstructing the label semantic space through joint label correlation to solve the multi-label weak-label classification task. Specifically, we leverage the label information consistency and feature-label dependency assumptions to reconstruct the semantic space and consider label correlations to enhance the information of semantic views. Moreover, l2,1-norm is utilized to mitigate the effect of missing label space noise. Additionally, the linear model of the proposed method is expanded to a nonlinear version of the kernel method to address the problem of the inseparability of linear data. Extensive experiments on several real-world tasks show that the proposed method outperforms some state-of-the-art methods.

A Multi-Objective online streaming Multi-Label feature selection using mutual information

Multi-label classification methods aim at assigning more than one label to each instance. In many real-world classification problems such as image multi-label classification tasks such as cancer detection, and text classification, we faced with thousands of thousand features. The performance of machine learning methods will be reduced while faced with high dimensional problems. To tackle this issue, feature selection methods are introduced to choose a small set of prominent features which best describe the data. Traditional multi-label feature selection methods are required to access to whole feature space, while in online platforms such as Facebook and Twitter, we faced with streams of data added by the users of these platforms over the time. Traditional multi-label feature selection methods are failed while applied on data streams. To solve this issue, online methods are introduced to deal with data streams. Existing streaming multi-label feature selection methods consider the task as a single optimization process while there are several contradictory objectives that need to be optimize simultaneously. To solve this issue, this paper uses a multi-objective search strategy to choose streaming features by using the mutual information and Pareto optimal set theories. There are several objectives such as minimizing the redundancy of features, and maximizing the relevancy of features to a set of labels that are need to be optimized during the feature selection process. Here, we used the Pareto set theory to identify a set of no-dominant solutions which best describe the problem. The proposed method has compared with a set of state-of-the-art online feature selection methods and the obtained results demonstrate the effectiveness of the proposed strategy.

Multi-source domain adaptation method for textual emotion classification using deep and broad learning

Existing domain adaptation methods for classifying textual emotions have the propensity to focus on single-source domain exploration rather than multi-source domain adaptation. The efficacy of emotion classification is hampered by the restricted information and volume from a single source domain. Thus, to improve the performance of domain adaptation, we present a novel multi-source domain adaptation approach for emotion classification, by combining broad learning and deep learning in this article. Specifically, we first design a model to extract domain-invariant features from each source domain to the same target domain by using BERT and Bi-LSTM, which can better capture contextual features. Then we adopt broad learning to train multiple classifiers based on the domain-invariant features, which can more effectively conduct multi-label classification tasks. In addition, we design a co-training model to boost these classifiers. Finally, we carry out several experiments on four datasets by comparison with the baseline methods. The experimental results show that our proposed approach can significantly outperform the baseline methods for textual emotion classification.