Multi-label Classification Methods Research Articles

Global-guided weakly-supervised learning for multi-label image classification

Multi-label classification with region-free labels is attracting increasing attention compared to that with region-based labels due to the time-consuming manual region-labeling process. Existing methods usually employ attention-based technology to discover the conspicuous label-related regions in a weakly-supervised manner with only image-level region-free labels, while the region covering is not precise without exploring global clues of multi-level features. To address this issue, a novel Global-guided Weakly-Supervised Learning (GWSL) method for multi-label classification is proposed. The GWSL first extracts the multi-level features to estimate their global correlation map which is further utilized to guide feature disentanglement in the proposed Feature Disentanglement and Localization (FDL) networks. Specifically, the FDL networks then adaptively combine the different correlated features and localize the fine-grained features for identifying multiple labels. The proposed method is optimized in an end-to-end manner under weakly supervision with only image-level labels. Experimental results demonstrate that the proposed method outperforms the state-of-the-arts for multi-label learning problems on several publicly available image datasets. To facilitate similar researches in the future, the codes are directly available online at https://github.com/Yong-DAI/GWSL.

Label correlation embedding guided network for multi-label ECG arrhythmia diagnosis

In clinical practice, one patient may suffer from more than one arrhythmia simultaneously, that is, one ECG record may be associated with multiple types of arrhythmias. In fact, there are inherent dependencies between arrhythmias. However, previous studies have mainly focused on multi-class (single-label) ECG classification, which addresses each type of arrhythmia independently and ignores the multi-label correlation between different ECG abnormalities. To address the lack of ECG multi-label classification methods, we proposed a label correlation embedding guided network (LCEGNet) model to effectively recognize multi-label ECG arrhythmias and explore the correlation between ECG abnormalities. First, label correlation embedding was obtained based on the correlation matrix between different arrhythmias to guide feature extraction. Subsequently, the category-specific attention coefficient was obtained by calculating the cosine similarity coefficient between the label embedding and feature spaces. Experiments on public and self-collected ECG datasets were conducted. The LCEGNet achieved F1 scores of 0.777 and 0.872 and subset accuracy of 0.750 and 0.828 on the two datasets, respectively. A classification speed of 7.796ms was achieved. The experimental results demonstrate that the proposed LCEGNet achieved approximately a 11% and 9.1% improvement in the F1 score and subset accuracy, respectively, compared with traditional ResNet architecture and a 4.3% and 5.54% improvement in the F1 score and subset accuracy, respectively, compared with the state-of-the-art approaches.

Predicting Chemical End-of-Life Scenarios Using Structure-Based Classification Models.

Analyzing chemicals and their effects on the environment from a life cycle viewpoint can produce a thorough analysis that takes end-of-life (EoL) activities into account. Chemical risk assessment, predicting environmental discharges, and finding EoL paths and exposure scenarios all depend on chemical flow data availability. However, it is challenging to gain access to such data and systematically determine EoL activities and potential chemical exposure scenarios. As a result, this work creates quantitative structure-transfer relationship (QSTR) models for aiding environmental managment decision-making based on chemical structure-based machine learning (ML) models to predict potential industrial EoL activities, chemical flow allocation, environmental releases, and exposure routes. Further multi-label classification methods may improve the predictability of QSTR models according to the ML experiment tracking. The developed QSTR models will assist stakeholders in predicting and comprehending potential EoL management activities and recycling loops, enabling environmental decision-making and EoL exposure assessment for new or existing chemicals in the global marketplace.

PARIS: Partial instance and training set selection. A new scalable approach to multi-label classification

Multi-label classification has recently attracted research interest as a data mining task. Many current applications in data mining address problems that have instances belonging to more than one class. This requires the development of new efficient methods. Instance selection has been used in multi-label learning to improve the execution time and classification performance of many learning methods. Following the single-label approach, instance selection has been applied by selecting or unselecting the same instances for all labels. In this paper, we present a different and novel approach. An instance might be useful for some labels and harmful for others; therefore, our algorithm allows each instance to be discarded, selected, or only partially selected for use in the classification of certain labels. An extensive comparison using 45 datasets shows the usefulness of our approach in improving the current instance selection methods for multi-label problems, as well as the ability of our algorithm to compete with other more complex multi-label classification methods.

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.

Triple Alliance Prototype Orthotist Network for Long-Tailed Multi-Label Text Classification

Text classification, is one of the key tasks for representing the semantic information of documents, multi-label text classification (MLTC) is an important branch of it. MLTC aims to tag the most relevant labels for the given document. Compared to the standard multi-class case where each document has only one label, it is considerably more difficulty to annotate new coming documents for multi-label text classification. Furthermore, it also suffers from the challenge of highly skewed long-tailed label distribution. i.e., a few labels are associated with a large number of documents (a.k.a. head labels), while a large fraction of labels are associated with a small number of documents (a.k.a. tail labels). Due to the relative infrequency of tail labels, this leads to an imbalance that biases towards predicting more head labels. As challenging as this task is, it is an essential task to tackle since it represents many real-world cases, such as text retrieval of news. To address the challenge, we propose a Triple Alliance Prototype Orthotist Network (TAPON) to build a generic meta-mapping from few-shot prototypes to many-shot classifier parameters, which aims to promote the generalizability of tail classifiers. To be specific, TAPON is a two-stage method. At the first stage focusing on head labels, TAPON obtains the meta-knowledge between many-shot classifier parameters and few-shot prototype of head labels. Head label classifiers are trained by many-shot documents. Meanwhile, the triple alliance prototype is obtained by adopting an Attentive Prototype with the aid of few-shot documents, label semantic information and label correlation. Additionally, a Prototype Orthotist module is especially designed to capture the meta-knowledge between the many-shot classifier and few-shot prototype. At the second stage of transferring, TAPON aims to transfer the generic meta-mapping from head labels to tail labels. It first uses Attentive Prototype to obtain triple alliance prototype for tail labels, and then uses the meta-knowledge obtained from the first stage to get many-shot classifiers for tail labels. By conducting extensive experiments on four benchmark datasets, we show that the proposed TAPON significantly outperforms other state-of-the-art methods for long-tailed multi-label text classification.

Spatial Context-aware Object-attentional Network for Multi-label Image Classification.

Multi-label image classification is a fundamental but challenging task in computer vision. To tackle the problem, the label-related semantic information is often exploited, but the background context and spatial semantic information of related objects are not fully utilized. To address these issues, a multi-branch deep neural network is proposed in this paper. The first branch is designed to extract the discriminant information from regions of interest to detect target objects. In the second branch, a spatial context-aware approach is proposed to better capture the contextual information of an object in its surroundings by using an adaptive patch expansion mechanism. It helps the detection of small objects that are easily lost without the support of context information. The third one, the object-attentional branch, exploits the spatial semantic relations between the target object and its related objects, to better detect partially occluded, small or dim objects with the support of those easily detectable objects. To better encode such relations, an attention mechanism jointly considering the spatial and semantic relations between objects is developed. Two widely used benchmark datasets for multi-labeling classification, MS COCO and PASCAL VOC, are used to evaluate the proposed framework. The experimental results demonstrate that the proposed method outperforms the state-of-the-art methods for multi-label image classification.

Research on the Multilabel Data Stream Classification Method Based on Fuzzy Complex Set‐Valued Measure Learning

In the process of modern industrial production equipment developing towards the direction of structure, automation, and intelligence, motor is still the main power output equipment. If the data flow classification occurs during the operation of the motor, it will lead to problems such as the reduction of its operation efficiency and the increase in system energy consumption. In serious cases, it will even cause motor damage, and the overall system equipment will be shut down for maintenance for a long time, resulting in serious economic losses. Therefore, the research on intelligent multilabel data stream classification technology of motor is of great significance to ensure the stability and reliability of efficient operation of production equipment. In order to improve the recognition efficiency and accuracy of ms‐1dcnn’s multilabel data stream classification method in the environment of variable motor conditions and strong noise interference, a multiscale feature fusion framework is constructed based on the residual network structure. The implementation principles of two kinds of attention mechanism algorithms, squeeze and excitation module and convolution attention module, are studied, respectively. The attention module suitable for one‐dimensional residual network is designed and embedded into the residual module to build a multiscale attention residual network model. Finally, the effectiveness and superiority of the proposed model are verified by using the experimental platform data.

Toward Purifying Defect Feature for Multilabel Sewer Defect Classification

An automatic vision-based sewer inspection plays a key role of sewage system in a modern city. Recent advances focus on utilizing deep learning model to realize the sewer inspection system, benefiting from the capability of data-driven feature extraction. However, the ambiguity of sewer defects in the feature space is ignored, deteriorating the performance of sewer inspection. There are two reasons for such ambiguity. First, the defect-irrelevant region interferes the feature extraction of the model. Second, the setting of multi-label is an inherent challenge of extracting discriminative feature for different defect classes from defect-relevant region. In this paper, we propose a multi-label sewer defect classification method which can purify the sewer defect components in latent spaces, thereby mitigating the ambiguity of sewer defects. Specifically, a novel self-purification module (SPM) is modeled to disentangle the ambiguity of sewer defect feature, which consists of intra-class purification (ICP) and inter-class decorrelation (ICD). ICP utilizes the task-aware information to purify the sewer features, and ICD aims to eliminate the cross-correlation and defect-irrelevant components simultaneously. Moreover, to ensure the reliability of SPM, center global alignment (CGA) is introduced to avoid the trivial solution. Experimental results demonstrate the superiority of the proposed method compared with 7 state-of-the-art methods on the latest benchmark Sewer-ML. The proposed method outperforms the others approximately 8% F2 <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">CIW</sub> with a tolerant inference speed. Finally, the robustness of the proposed method is verified in two perturbed scenarios, where the reliable performance can be guaranteed against the limited perturbations.

Identifying Bacteria Species on Microscopic Polyculture Images Using Deep Learning.

Preliminary microbiological diagnosis usually relies on microscopic examination and, due to the routine culture and bacteriological examination, lasts up to 11 days. Hence, many deep learning methods based on microscopic images were recently introduced to replace the time-consuming bacteriological examination. They shorten the diagnosis by 1-2 days but still require iterative culture to obtain monoculture samples. In this work, we present a feasibility study for further shortening the diagnosis time by analyzing polyculture images. It is possible with multi-MIL, a novel multi-label classification method based on multiple instance learning. To evaluate our approach, we introduce a dataset containing microscopic images for all combinations of four considered bacteria species. We obtain ROC AUC above 0.9, proving the feasibility of the method and opening the path for future experiments with a larger number of species.

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.

Non-Aligned Multi-View Multi-Label Classification via Learning View-Specific Labels

In the multi-view multi-label (MVML) classification problem, multiple views are simultaneously associated with multiple semantic representations. Multi-view multi-label learning inevitably has the problems of consistency, diversity, and non-alignment among views and the correlation among labels. Most of the existing multi-view multi-label methods for non-aligned views assume that each view has a common or shared label set, but because a single view cannot contain the entire label information, they often learn suboptimal results. Based on this, this paper proposes a non-aligned multi-view multi-label classification method that learns view-specific labels (LVSL), aiming to explicitly mine the information of view-specific labels and low-rank label structures in non-aligned views in a unified model framework. Furthermore, to alleviate insufficient available label information, we thoroughly explored the global and local structural information among labels. Specifically, first, we assume that there is structural consistency between the view and the label space and then construct the view-specific label model in turn. Second, to enrich the original label space information, we mine the consistent information of multiple views and the low-rank correlation information hidden among multiple labels. Finally, the contribution weight of each view is combined with learning the complementary information among the views in the decision-making stage, and extend the model to handle nonlinear data. The results of the proposed method compared with existing state-of-the-art algorithms on several datasets validate its effectiveness.

Using Multi-Label Classification Methods to Analyze Complaints Against Cargo Services During the COVID-19 Outbreak: Comparing Survey-Based and Word-Based Labeling

This study investigates how cargo companies, with a significant market share in Turkey's service sector, managed their last-mile activities during the Covid-19 outbreak and suggests the solution to the adverse outcomes. The data used in the study included complaints made for cargo companies from an online complaint management website called sikayetvar.com from the start of the pandemic to the date of the research, which contained words related to the pandemic and was collected using Python language and the Scrapy module web scraping methods. Multilabel classification algorithms were used to categorize complaints based on assessments of training data obtained according to the topics. Results showed that parcel delivery-related themes were the most often complained about, and a considerable portion were delay issues.

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.

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-label multi-class COVID-19 Arabic Twitter dataset with fine-grained misinformation and situational information annotations.

Since the inception of the current COVID-19 pandemic, related misleading information has spread at a remarkable rate on social media, leading to serious implications for individuals and societies. Although COVID-19 looks to be ending for most places after the sharp shock of Omicron, severe new variants can emerge and cause new waves, especially if the variants can evade the insufficient immunity provided by prior infection and incomplete vaccination. Fighting the fake news that promotes vaccine hesitancy, for instance, is crucial for the success of the global vaccination programs and thus achieving herd immunity. To combat the proliferation of COVID-19-related misinformation, considerable research efforts have been and are still being dedicated to building and sharing COVID-19 misinformation detection datasets and models for Arabic and other languages. However, most of these datasets provide binary (true/false) misinformation classifications. Besides, the few studies that support multi-class misinformation classification deal with a small set of misinformation classes or mix them with situational information classes. False news stories about COVID-19 are not equal; some tend to have more sinister effects than others (e.g., fake cures and false vaccine info). This suggests that identifying the sub-type of misinformation is critical for choosing the suitable action based on their level of seriousness, ranging from assigning warning labels to the susceptible post to removing the misleading post instantly. We develop comprehensive annotation guidelines in this work that define 19 fine-grained misinformation classes. Then, we release the first Arabic COVID-19-related misinformation dataset comprising about 6.7K tweets with multi-class and multi-label misinformation annotations. In addition, we release a version of the dataset to be the first Twitter Arabic dataset annotated exclusively with six different situational information classes. Identifying situational information (e.g., caution, help-seeking) helps authorities or individuals understand the situation during emergencies. To confirm the validity of the collected data, we define three classification tasks and experiment with various machine learning and transformer-based classifiers to offer baseline results for future research. The experimental results indicate the quality and validity of the data and its suitability for constructing misinformation and situational information classification models. The results also demonstrate the superiority of AraBERT-COV19, a transformer-based model pretrained on COVID-19-related tweets, with micro-averaged F-scores of 81.6% and 78.8% for the multi-class misinformation and situational information classification tasks, respectively. Label Powerset with linear SVC achieved the best performance among the presented methods for multi-label misinformation classification with micro-averaged F-scores of 76.69%.

A General Framework for Class Label Specific Mutual Information Feature Selection Method

Information theory-based feature selection (ITFS) methods select a single subset of features for all classes based on the following criteria: 1) minimizing redundancy between the selected features and 2) maximizing classification information of the selected features with the classes. A critical issue with selecting a single subset of features is that they may not represent the feature space in which individual class labels can be separated exclusively. Existing methods fail to provide a way to select the feature space specific to the individual class label. To this end, we propose a novel feature selection method called class-label specific mutual information (CSMI) that selects a specific set of features for each class label. The proposed method maximizes the information shared among the selected features and target class label but minimizes the same with all classes. We also consider the dynamic change of information between selected features and the target class label when a candidate feature is added. Finally, we provide a general framework for the CSMI to make it classifier-independent. We perform experiments on sixteen benchmark data sets using four classifiers and found that the CSMI outperforms five traditional, two state-of-the-art ITFS (multi-class classification), and one multi-label classification methods.

Retracted: Complexity Graph-Based Multilabel Classification Method of Human Action in Rope Skipping Scene

Retracted: Complexity Graph-Based Multilabel Classification Method of Human Action in Rope Skipping Scene

Multi-label classification of Alzheimer's disease stages from resting-state fMRI-based correlation connectivity data and deep learning

Alzheimer's disease is a neurodegenerative condition that gradually impairs cognitive abilities. Recently, various neuroimaging modalities and machine learning methods have surfaced to diagnose Alzheimer's disease. Resting-state fMRI is a neuroimaging modality that has been widely utilized to study brain activity related to neurodegenerative diseases. In literature, the previous studies are limited to the binary classification of Alzheimer's disease and Mild Cognitive Impairment. The application of computer-aided diagnosis for the numerous advancing phases of Alzheimer's disease, on the other hand, remains understudied. This research analyzes and presents methods for multi-label classification of six Alzheimer's stages using rs-fMRI and deep learning. The proposed model solves the multi-class classification problem by extracting the brain's functional connectivity networks from rs-fMRI data and employing two deep learning approaches, Stacked Sparse Autoencoder and Brain Connectivity Graph Convolutional Network. The suggested models' results were assessed using the k-fold cross-validation approach, and an average accuracy of 77.13% and 84.03% was reached for multi-label classification using Stacked Sparse Autoencoders and Brain Connectivity Based Convolutional Network, respectively. An analysis of brain regions was also performed by using the network's learned weights, leading to the conclusion that the precentral gyrus, frontal gyrus, lingual gyrus, and supplementary motor area are the significant brain regions of interest.

Prompt Tuning for Multi-Label Text Classification: How to Link Exercises to Knowledge Concepts?

Exercises refer to the evaluation metric of whether students have mastered specific knowledge concepts. Linking exercises to knowledge concepts is an important foundation in multiple disciplines such as intelligent education, which represents the multi-label text classification problem in essence. However, most existing methods do not take the automatic linking of exercises to knowledge concepts into consideration. In addition, most of the widely used approaches in multi-label text classification require large amounts of training data for model optimization, which is usually time-consuming and labour-intensive in real-world scenarios. To address these problems, we propose a prompt tuning method for multi-label text classification, which can address the problem of the number of labelled exercises being small due to the lack of specialized expertise. Specifically, the relevance scores of exercise content and knowledge concepts are learned by a prompt tuning model with a unified template, and then the multiple associated knowledge concepts are selected with a threshold. An Exercises–Concepts dataset of the Data Structure course is constructed to verify the effectiveness of our proposed method. Extensive experimental results confirm our proposed method outperforms other state-of-the-art baselines by up to 35.53% and 41.78% in Micro and Macro F1, respectively.