Explore the vast range of titles available.

Extreme multi-label classification (XMC) refers to supervised multi-label learning involving hundreds of thousands or even millions of labels. In this paper, we develop a suite of algorithms, called Bonsai, which generalizes the notion of label representation in XMC, and partitions the labels in the representation space to learn shallow trees. We show three concrete realizations of this label representation space including: (i) the input space which is spanned by the input features, (ii) the output space spanned by label vectors based on their co-occurrence with other labels, and (iii) the joint space by combining the input and output representations. Furthermore, the constraint-free multi-way partitions learnt iteratively in these spaces lead to shallow trees. By combining the effect of shallow trees and generalized label representation, Bonsai achieves the best of both worlds—fast training which is comparable to state-of-the-art tree-based methods in XMC, and much better prediction accuracy, particularly on tail-labels. On a benchmark Amazon-3M dataset with 3 million labels, Bonsai outperforms a state-of-the-art one-vs-rest method in terms of prediction accuracy, while being approximately 200 times faster to train. The code for Bonsai is available at https://github.com/xmc-aalto/bonsai.

Featured Application: The method presented in this paper can be applied in medical computer systems for supporting medical diagnosis.Abstract: Thoracic radiography (chest X-ray) is an inexpensive but effective and widely used medical imaging procedure. However, a lack of qualified radiologists severely limits the applicability of the technique. Even current Deep Learning-based approaches often require strong supervision, e.g., annotated bounding boxes, to train such systems, which is impossible to harvest on a large scale. In this work, we proposed the classification and prediction of lung pathologies of frontal thoracic X-rays using a modified model MobileNet V2. We considered using transfer learning with metadata leverage. We used the NIH Chest-Xray-14 database, and we did a comparison of performance of our approach to other state-of-the-art methods for pathology classification. The main comparison was by Area under the Receiver Operating Characteristic Curve (AUC) statistics and analyzed the differences between classifiers. Overall, we notice a considerable spread in the achieved result with an average AUC of 0.811 and an accuracy above 90%. We conclude that resampling the dataset gives a huge improvement to the model performance. In this work, we intended to create a model that is capable of being trained, and modified devices with low computing power because they can be implemented into smaller IoT devices.

Despite significant advancements in multi-view multi-label learning driven by its broad applicability, real-world scenarios frequently suffer from dual incompleteness in both view and label spaces due to data acquisition uncertainties. The incompleteness of multi-view features degrades the comprehensiveness of sample representations, leading to failure in capturing semantically discriminative patterns essential for classification. To address the aforementioned challenges, we propose a novel learning framework termed V iew- L abel Driven C ross-Space S tructure A lignment Network (VLCSA). Departing from existing low-quality view completion approaches, we devise a view-label hybrid-driven autoencoder (VLAE) that extracts discriminative view-specific features through joint optimization of cross-view semantic consistency and label-guided instance-level embeddings, which allows for accurate reconstruction of missing views. Furthermore, we propose cross-space structure alignment (CSA), which imposes view-label hybrid-driven losses on both original and complete feature spaces to enforce structural consistency between partial and holistic semantic topologies. Recognizing the suboptimal data reconstruction quality during initial training phases, we propose phase-aware excitation (PAE) to mitigate error accumulation in early-stage learning. Additionally, we introduce star-shaped interactive sharing module (SIS) that facilitates efficient cross-view information exchange while leveraging view complementarity to ensure consistent and robust feature aggregation, circumventing conflicts with view-consistency alignment objectives. d on five widely-adopted benchmark datasets indicate that the proposed VLCSA framework outperforms numerous established baselines in terms of comprehensive evaluation metrics.

Recently, multi-view multi-label learning has gained significant attention due to its applicability in various domains. However, due to the limitations of data collection and the subjectivity of manual labeling, multi-view multi-label learning often faces both partial views and incomplete labels, substantially impacting the performance of existing classification methods in practical applications. Although existing methods have attempted to address this issue, they struggle to fully exploit the consistency and complementarity of multi-view multi-label data simultaneously. To overcome this limitation, we propose a novel structure-guided decoupled contrastive framework (SGDC). Specifically, to address the limitations of conventional single-encoder paradigms, SGDC innovatively incorporates a decoupled disentanglement mechanism (DDM). By integrating a dual-encoder architecture with mutual information upper bound constraints, DDM decouples multi-view features into view-specific and view-consistent components, which can improve the quality of feature representations. Additionally, the SGDC integrates a structure-guided contrastive (SGC) framework that performs dynamic semantic alignment in consistent feature spaces through global structural modeling, effectively implementing structure-conscious representation learning guided by the multi-view consensus principle. Experimental results on multiple datasets consistently demonstrate the effectiveness of our method in handling complex multi-view multi-label data.

Multi-label classification (MLC) is a very explored field in recent years. The most common approaches that deal with MLC problems are classified into two groups: (i) problem transformation which aims to adapt the multi-label data, making the use of traditional binary or multiclass classification algorithms feasible, and (ii) algorithm adaptation which focuses on modifying algorithms used into binary or multiclass classification, enabling them to make multi-label predictions. Several approaches have been proposed aiming to explore the relationships among the labels, with some of them through the transformation of a flat multi-label label space into a hierarchical multi-label label space, creating a tree-structured label taxonomy and inducing a hierarchical multi-label classifier to solve the classification problem. This paper presents a novel method in which a label hierarchy structured as a directed acyclic graph (DAG) is created from the multi-label label space, taking into account the label co-occurrences using the notion of closed frequent labelset. With this, it is possible to solve an MLC task as if it was a hierarchical multi-label classification (HMC) task. Global and local HMC approaches were tested with the obtained label hierarchies and compared with the approaches using tree-structured label hierarchies showing very competitive results. The main advantage of the proposed approach is better exploration and representation of the relationships between labels through the use of DAG-structured taxonomies, improving the results. Experimental results over 32 multi-label datasets from different domains showed that the proposed approach is better than related approaches in most of the multi-label evaluation measures and very competitive when compared with the state-of-the-art approaches. Moreover, we found that both tree and in specially DAG-structured label hierarchies combined with a local hierarchical classifier are more suitable to deal with imbalanced multi-label datasets.

We address the task of learning ensembles of predictive models for structured output prediction (SOP). We focus on three SOP tasks: multi-target regression (MTR), multi-label classification (MLC) and hierarchical multi-label classification (HMC). In contrast to standard classification and regression, where the output is a single (discrete or continuous) variable, in SOP the output is a data structure—a tuple of continuous variables MTR, a tuple of binary variables MLC or a tuple of binary variables with hierarchical dependencies (HMC). SOP is gaining increasing interest in the research community due to its applicability in a variety of practically relevant domains. In this context, we consider the Extra-Tree ensemble learning method—the overall top performer in the DREAM4 and DREAM5 challenges for gene network reconstruction. We extend this method for SOP tasks and call the extension Extra-PCTs ensembles. As base predictive models we propose using predictive clustering trees (PCTs)–a generalization of decision trees for predicting structured outputs. We conduct a comprehensive experimental evaluation of the proposed method on a collection of 41 benchmark datasets: 21 for MTR, 10 for MLC and 10 for HMC. We first investigate the influence of the size of the ensemble and the size of the feature subset considered at each node. We then compare the performance of Extra-PCTs to other ensemble methods (random forests and bagging), as well as to single PCTs. The experimental evaluation reveals that the Extra-PCTs achieve optimal performance in terms of predictive power and computational cost, with 50 base predictive models across the three tasks. The recommended values for feature subset sizes vary across the tasks, and also depend on whether the dataset contains only binary and/or sparse attributes. The Extra-PCTs give better predictive performance than a single tree (the differences are typically statistically significant). Moreover, the Extra-PCTs are the best performing ensemble method (except for the MLC task, where performances are similar to those of random forests), and Extra-PCTs can be used to learn good feature rankings for all of the tasks considered here.

Labeling issues with the skills required to complete them can help contributors to choose tasks in Open Source Software projects. However, manually labeling issues is time-consuming and error-prone, and current automated approaches are mostly limited to classifying issues as bugs/non-bugs. We investigate the feasibility and relevance of automatically labeling issues with what we call “API-domains,” which are high-level categories of APIs. Therefore, we posit that the APIs used in the source code affected by an issue can be a proxy for the type of skills (e.g., DB, security, UI) needed to work on the issue. We ran a user study (n=74) to assess API-domain labels’ relevancy to potential contributors, leveraged the issues’ descriptions and the project history to build prediction models, and validated the predictions with contributors (n=20) of the projects. Our results show that (i) newcomers to the project consider API-domain labels useful in choosing tasks, (ii) labels can be predicted with a precision of 84% and a recall of 78.6% on average, (iii) the results of the predictions reached up to 71.3% in precision and 52.5% in recall when training with a project and testing in another (transfer learning), and (iv) project contributors consider most of the predictions helpful in identifying needed skills. These findings suggest our approach can be applied in practice to automatically label issues, assisting developers in finding tasks that better match their skills.

Multi-label classification (MLC) is a very interesting and important domain that has attracted many researchers in the last two decades. Several single-label classification algorithms that belong to different learning strategies have been adapted to handle the problem of MLC. Surprisingly, no Associative Classification (AC) algorithm has been adapted to handle the MLC problem, where AC algorithms have shown a high predictive performance compared with other learning strategies in single-label classification. In this paper, a deep investigation regarding utilizing AC in MLC is presented. An evaluation of several AC algorithms on three multi-label datasets with respect to five discretization techniques revealed that utilizing AC algorithms in MLC is very promising compared with other algorithms from different learning strategies.

Clouds of various kinds play a substantial role in a wide variety of atmospheric processes. They are directly linked to the formation of precipitation, and significantly affect the atmospheric energy budget via radiative effects and latent heat. Moreover, knowledge of currently occurring cloud types allows the observer to draw conclusions about the short‐term evolution of the state of the atmosphere and the weather. Therefore, a consistent cloud classification scheme has already been introduced almost 100 years ago. In this work, we train an ensemble of identically initialized multi‐label residual neural network architectures from scratch with ground‐based RGB pictures. Operational human observations, consisting of up to three out of 30 cloud classes per instance, are used as ground truth. To the best of our knowledge, we are the first to classify clouds with this methodology into 30 different classes. Class‐specific resampling is used to reduce prediction biases due to a highly imbalanced ground truth class distribution. Results indicate that the ensemble mean outperforms the best single member in each cloud class. Still, each single member clearly outperforms both random and climatological predictions. Attributes diagrams indicate underconfidence in heavily augmented classes and very good calibration in all other classes. Autonomy and output consistency are the main advantages of such a trained classifier, hence we consider operational cloud monitoring as main application. Either for consistent cloud class observations or to observe the current state of the weather and its short time evolution with high temporal resolution, for example, in proximity of solar power plants. Plain Language Summary Monitoring clouds in the sky can give experts important information on the current and upcoming weather, as well as other processes in the atmosphere. Machine learning models, more specifically so‐called Convolutional Neural Networks, can be trained to constantly and automatically retrieve this information. This is done by repeatedly showing the model pictures of the sky in combination with cloud classes, which are visible on these pictures and have been determined by human experts in the past. During this process, the model learns distinctive visual properties of each class and can at some point correctly predict cloud classes from previously unseen pictures. In this work, we trained such models to find up to three out of 30 different cloud classes for each picture, in order to mimic human operational observations. Results show, that our model has overall a good performance but suffers from data shortage in specific classes, which may reduce applicability. However, our work can be considered a decent starting point, since in the future a larger data set or an even more sophisticated method may resolve this issue. Key Points ResNets can accurately and reliably classify clouds into 30 World Meteorological Organization cloud classes from ground‐based RGB pictures Class‐specific data augmentation substantially reduces prediction biases and enables successful model training but introduces overfitting Ensemble mean predictions outperform single members in all classes

Selecting an appropriate population pharmacokinetic (PK) model for individual patients in model‐informed precision dosing (MIPD) can be challenging, particularly in the absence of therapeutic drug monitoring (TDM) samples. We developed a machine learning (ML) model to guide individualized PK model selection for a priori MIPD of vancomycin based on routinely recorded patient characteristics. This retrospective analysis included 343,636 vancomycin TDM records, each from a distinct adult patient across 156 healthcare centers, along with a priori predictions from six PK models. A multi‐label classification approach was applied, labeling PK model predictions based on whether they fell within 80%–125% of observed TDM values. Various modeling strategies were evaluated using XGBoost as the base algorithm, with binary relevance selected for the final model. At the prediction stage, PK models were ranked and averaged for each patient based on ML‐predicted probabilities that predictions would fall within 80%–125% of the observed concentration. Selecting the highest ranked PK model for each patient and ML‐based model averaging outperformed all single PK models, body mass index‐based selection, and naive averaging. On a population level, these ML approaches resulted in more accurate predictions, a higher proportion of predictions within 80%–125% of observed vancomycin concentrations, and no systematic bias. Predictive performance declined with lower ML‐assigned rankings, and selecting the lowest‐ranked PK model for each patient resulted in worse performance than the worst‐performing single PK model. By guiding the selection of appropriate models and avoiding less suitable ones, ML approaches for a priori MIPD may improve early dosing decisions. Schematic overview of the workflow used to train and apply the multi‐label classification model for PK model selection and averaging in a priori vancomycin precision dosing.