Classification is a crucial process in data mining, data science, machine learning, and the applications of natural language processing. Classification methods distinguish the correlation between the data and the output classes. In single-label classification (SLC), each input sample is associated with only one class label. In certain real-world applications, data instances may be assigned to more than one class. The type of classification which is required in such applications is known as Multi-label classification (MLC). In MLC, each sample of data is associated with a set of labels. Due to the presence of Multiple class labels, the SLC learning process is not applicable to MLC tasks. Many solutions to the Multi-label classification problem have been proposed, including BR, FS-DR, and LLSF. But, these methods are not as accurate as they could be. In this paper, a new Multi-label classification method is proposed based on graph representation. A feature selection technique and the Q-learning method are employed to increase the accuracy of the proposed algorithm. The proposed Multi-label classification algorithm is applied to various standard Multi-label datasets. The results are compared with state-of-the-art algorithms based on the well-known performance evaluation metrics. Experimental results demonstrated the effectiveness of the proposed model and its superiority over the other methods.

Multi-label classification assigns Multiple labels to each instance, crucial for tasks like cancer detection in images and text categorization. However, machine learning methods often struggle with the complexity of real-life datasets. To improve efficiency, researchers have developed feature selection methods to identify the most relevant features. Traditional methods, requiring all features upfront, fail in dynamic environments like media platforms with continuous data streams. To address this, novel online methods have been created, yet they often neglect optimizing conflicting objectives. This study introduces an objective search approach using mutual information, feature interaction, and the NSGA-II algorithm to select relevant features from streaming data. The strategy aims to minimize feature overlap, maximize relevance to labels, and optimize online feature interaction analysis. By applying a modified NSGA-II algorithm, a set of non-dominantsolutions is identified. Experiments on eleven datasets show that the proposed approach outperforms advanced online feature selection techniques in predictive accuracy, statistical analysis, and stability assessment.

Multi-label classification has many applications in the text categorization, biology, and medical diagnosis, in which Multiple class labels can be assigned to each training instance simultaneously. As it is often the case that there are relationships between the labels, extracting the existing relationships between the labels and taking advantage of them during the training or prediction phase can bring about significant improvements. In this paper, we introduce positive, negative, and hybrid relationships between the class labels for the first time, and propose a method to extract these relations for a Multi-label classification task, and to use them consequently in order to improve the predictions made by a Multi-label classifier. We conduct extensive experiments to assess the effectiveness of the proposed method. The results obtained advocate the merits of the proposed method in improving the Multi-label classification results.

Multi-label classification has gained significant attention during recent years, due to the increasing number of modern applications associated with Multi-label data. Despite its short life, different approaches have been presented to solve the task of Multi-label classification. LIFT is a Multi-label classifier which utilizes a new strategy to Multi-label learning by leveraging label-specific features. label-specific features means that each class label is supposed to have its own characteristics and is determined by some specific features that are the most discriminative features for that label. LIFT employs clustering methods to discover the properties of data. More precisely, LIFT divides the training instances into positive and negative clusters for each label which respectively consist of the training examples with and without that label. It then selects representative centroids in the positive and negative instances of each label by k-means clustering and replaces the original features of a sample by the distances to these representatives. Constructing new features, the dimensionality of the new space reduces significantly. However, to construct these new features, the original features are needed. Therefore, the complexity of the process of Multi-label classification does not diminish, in practice. In this paper, we make a modification on LIFT to reduce the computational burden of the classifier and improve or at least preserve the performance of it, as well. The experimental results show that the proposed algorithm has obtained these goals, simultaneously.

Multi-label text classification is a critical challenge in natural language processing, where the goal is to assign Multiple labels to a given document. Recent advances have primarily focused on deep learning approaches, yet many fail to adequately capture the intricate relationships between documents and labels. In this paper, we propose a novel method called MultiCGCN, in which we leverage Graph Convolutional Networks (GCNs) for Multi-label text classification by modeling text as a heterogeneous graph. This unified graph incorporates document similarities, label relationships, and document-label associations, enabling the model to effectively capture both document and label dependencies. We transform the Multi-label classification problem into a link prediction task, using Term Frequency–Inverse Document Frequency (TF-IDF) for document similarity and applying GCNs to predict label assignments. Our empirical evaluations demonstrate that MultiCGCN achieves a significant performance boost, improving F1 score by 10% over traditional baseline models. This approach opens new avenues for enhancing the accuracy of Multi-label classification in various domains.

This paper explores graph embedding techniques for effectively analyzing large, heterogeneous graphs with complex and noisy patterns. Graphs represent data through nodes (entities) and edges (relationships), and when dealing with large-scale data, effective search methods are crucial. Graph embedding helps evaluate node significance and transforms data into latent space representations. It also addresses challenges like handling Multi-label data in heterogeneous networks, where nodes may have Multiple labels describing complex concepts. Traditional methods struggle with such Multi-label scenarios and fail to capture label dependencies. The paper introduces a Graph Neural Network (GCN)-based node embedding method, which extends traditional neural networks to graph data. GCNs allow the extraction of local features from nodes and their neighbors, making them useful for heterogeneous networks. By integrating label information into the embedding process, the method improves relationships between labels. The proposed approach transforms neighboring labels into continuous vectors, structured into a matrix for learning. This enhances the overall network embedding. The method outperforms previous techniques, demonstrating improved performance on real-world datasets, such as a 2.4% improvement on the IMDB dataset and 9.3% on the DBLP dataset. The paper discusses graph embedding techniques in the first section and explores the potential of Multi-label embedding in non-uniform graphs, suggesting future research directions in the final section. The article's code link on GitHub can also be found at the following: https://github.com/frshkara/EGSA.

Recently, many neural network methods have been proposed for Multilabel classification in the literature. One of these recent methods is the Multi-Layer Extreme Learning Machines (ML-ELMs) in which stack auto encoders are used for tuning their weights. However, ML-ELMs suffer from three primary drawbacks: First, input weights and biases are chosen randomly; second, the pseudoinverse solution for calculating output weights will increase the reconstruction error; third, memory and execution time of transformation matrices are proportional to the number of hidden layers. In this paper, Multi-Layer Kernel Extreme Learning Machine (ML-CK-ELM) that uses a linear combination of base kernels in each layer is proposed for Multi-label classification. The proposed approach effectively addresses the above-mentioned drawbacks. Furthermore, Multi-label classification data are inherently characterized by Multi-modal aspects due to a variety of labels assigned to each instance. Applying a combination of different kernels is the added advantage of ML-CK-ELM that implicitly assesses the inherent Multi-modal aspects of Multi-label data; each kernel can be effectively used to cover one of the modals better than other kernels. The empirical study indicates that ML-CK-ELM shows competitively better performance than other state-of-the-art methods, and experimental results of Multilabel datasets verify the feasibility of ML-CK-ELM.