BIT-WOW at NLPCC-2022 Task5 Track1: Hierarchical Multi-label Classification via Label-Aware Graph Convolutional Network

BackgroundPrinted or scanned ECG strips remain crucial in low-resource settings where digital waveform data are unavailable. Most deep learning approaches depend on raw signal inputs and often struggle to model rhythm-specific features or account for the hierarchical structure of ECG abnormalities. We hypothesised that combining ECG strip images with rhythm-sensitive Continuous Wavelet Transform (CWT) maps, alongside curriculum learning and graph-based label refinement, could improve multi-label ECG classification from visual data alone.PurposeTo develop PulseFormer, a hierarchical ECG image classification model using bimodal co-attention, graph-refined label embeddings, and curriculum learning to predict 18 diagnostic classes from ECG and wavelet-derived inputs.MethodsWe used PTB-XL, a large public dataset of 12-lead ECG signals recorded at 100 Hz over 10 seconds. Signals were plotted to simulate printed strips, preprocessed with Hough transform for gridline removal, and binarised to enhance waveform visibility. CWT images were generated from these simulated ECG plots.PulseFormer was trained on 17,144 ECG–CWT image pairs and tested on 2,241. ECG and CWT modalities were processed through separate CNN stems and Vision Transformer (ViT-Small, initialised with ImageNet weights) encoders, then fused via bimodal co-attention. Curriculum learning was applied by sequentially introducing increasingly fine-grained classification tasks—first normal vs abnormal, then superclass, and finally subclass labels—to encourage faster convergence and better feature space separation. Auxiliary subclass classification heads were attached at the ViT level to improve gradient flow and early feature optimisation for superior sub class discrimination.Label embeddings were refined using a Graph Convolutional Network (GCN) based on predefined superclass–subclass relationships. Subclass outputs were softly gated by superclass probabilities, allowing controlled multi-label predictions. Grid-searched thresholds were used to calibrate the outputs, as seen in Figure 1. The model was trained using the Adam optimiser (learning rate 1e-4) with weight decay and cosine annealing. Weighted focal binary cross entropy loss and oversampling addressed severe class imbalance. Training ran for up to 36 epochs with early stopping, using a single NVIDIA RTX 4060 GPU.ResultsPulseFormer achieved a macro F1 of 0.68, AUC of 0.92, and overall accuracy of 88 percent. Stage-wise: normal vs abnormal (0.84 accuracy, 0.82 F1, 0.90 AUC), superclass (0.85 accuracy, 0.71 F1, 0.84 AUC), and subclass (0.93 accuracy, 0.65 F1, 0.93 AUC), as seen in Figure 2.ConclusionsPulseFormer enables accurate, structured, and multi-label ECG classification from image-based inputs, with the highest number of diagnostic classes covered in recent works. Its design supports scalable deployment in environments lacking raw waveform access, while promoting generalisable, hierarchy-aware diagnostic prediction.Figure 1PulseFormer architectureFigure 2Class wise results

This paper proposes a hierarchical multi-label classification method based on SVM with composite kernel for solving gene function prediction. The hierarchical multi-label classification problem is resolved into a set of binary classification tasks. A composite kernel based SVM (ck-SVM) is introduced to deal with the binary classification tasks. In estimation procedure of ck-SVM, a supervised clustering with over-sampling strategy is introduced for solving imbalance dataset learning problem and improve classification performance. Experimental results on benchmark datasets demonstrate that the proposed method improves the classification performance efficiently.

In this paper, we present a hierarchical multi-label classification system for visual concepts detection and image annotation. Hierarchical multi-label classification (HMLC) is a variant of classification where an instance may belong to multiple classes at the same time and these classes/labels are organized in a hierarchy. The system is composed of two parts: feature extraction and classification/annotation. The feature extraction part provides global and local descriptions of the images. These descriptions are then used to learn a classifier and to annotate an image with the corresponding concepts. To this end, we use predictive clustering trees (PCTs), which are able to classify target concepts that are organized in a hierarchy. Our approach to HMLC exploits the annotation hierarchy by building a single predictive clustering tree that can simultaneously predict all of the labels used to annotate an image. Moreover, we constructed ensembles (random forests) of PCTs, to improve the predictive performance. We tested our system on the image database from the ImageCLEF@ICPR 2010 photo annotation task. The extensive experiments conducted on the benchmark database show that our system has very high predictive performance and can be easily scaled to large number of visual concepts and large amounts of data.

Deep hiearchical multi-label classification applied to chest X-ray abnormality taxonomies.

Major depressive disorder (MDD) is characterized by impairments in mood and cognitive functioning, and it is a prominent source of global disability and stress. A functional magnetic resonance imaging (fMRI) can aid clinicians in their assessments of individuals for the identification of MDD. Herein, we employ a deep learning approach to the issue of MDD classification. Resting-state fMRI data from 821 individuals with MDD and 765 healthy controls (HCs) is employed for investigation. An ensemble model based on graph neural network (GNN) has been created with the goal of identifying patients with MDD among HCs as well as differentiation between first-episode and recurrent MDDs. The graph convolutional network (GCN), graph attention network (GAT), and GraphSAGE models serve as a base models for the ensemble model that was developed with individual whole-brain functional networks. The ensemble's performance is evaluated using upsampling and downsampling, along with 10-fold cross-validation. The ensemble model achieved an upsampling accuracy of 71.18% and a downsampling accuracy of 70.24% for MDD and HC classification. While comparing first-episode patients with recurrent patients, the upsampling accuracy is 77.78% and the downsampling accuracy is 71.96%. According to the findings of this study, the proposed GNN-based ensemble model achieves a higher level of accuracy and suggests that our model produces can assist healthcare professionals in identifying MDD.

Skeleton-based action recognition aims to project skeleton sequences to action categories, where skeleton sequences are derived from multiple forms of pre-detected points. Compared with earlier methods that focus on exploring single-form skeletons via Graph Convolutional Networks (GCNs), existing methods tend to improve GCNs by leveraging multi-form skeletons due to their complementary cues. However, these methods (either adapting structure of GCNs or model ensemble) require the co-existence of all forms of skeletons during both training and inference stages, while a typical situation in real life is the existence of only partial forms for inference. To tackle this issue, we present Adaptive Cross-Form Learning (ACFL), which empowers well-designed GCNs to generate complementary representation from single-form skeletons without changing model capacity. Specifically, each GCN model in ACFL not only learns action representation from the single-form skeletons, but also adaptively mimics useful representations derived from other forms of skeletons. In this way, each GCN can learn how to strengthen what has been learned, thus exploiting model potential and facilitating action recognition as well. Extensive experiments conducted on three challenging benchmarks, i.e., NTU-RGB+D 120, NTU-RGB+D 60 and UAV-Human, demonstrate the effectiveness and generalizability of the proposed method. Specifically, the ACFL significantly improves various GCN models (i.e., CTR-GCN, MS-G3D, and Shift-GCN), achieving a new record for skeleton-based action recognition.

CEHMR: Curriculum learning enhanced hierarchical multi-label classification for medication recommendation

The classification problems described in the Machine Learning literature usually relate to the classification of data in which each example is associated to a class belonging to a finite set of classes, all at the same level. However, there are classification issues, of a hierarchical nature, where the classes can be either subclasses or super classes of other classes. In many hierarchical problems, one or more examples may be associated with more than one class simultaneously. These problems are known as hierarchical multi-label classification (HMC) problems. In this work, the ML-KNN algorithm was used to predict hierarchical multi-label problems, in order to determine the number of classes that can be assigned to an example. Through the experiments performed on 10 protein function databases and the statistical analysis of the results, it can be shown that the adaptations performed in the ML-KNN algorithm brought significant performance improvements based on the hierarchical precision and recall metrics Hierarchical.

Hierarchical Classification is a very important classification task for arranging data in a hierarchical structure. Hierarchical arrangement of data is one of the best methods to achieve better understanding of complex data. In this paper, we propose the HMAC method to perform Hierarchical Multi-label Associative Classification. This method uses multiple and negative rules to predict class-set and to filter exceptional cases in order to improve both accuracy and explanatory ability of the resulting classifier. Redundant rule pruning method for negative rules and rule ranking method for hierarchical associative classification are developed. Moreover, we propose a rule evaluation measure, Sim, that tread-off between F-measure and Jaccard's coefficient to encode hierarchical structure meaning of actual and predicted node collections. We show that Sim is robust and simple rule evaluation measure. Experimental results show that HMAC improves accuracy and explanatory ability of hierarchical classifiers compared with various rule ranking and pruning techniques.

Hyperspectral unmixing aims to estimate endmember spectra and their corresponding abundance fractions at the subpixel scale, which is a critical preprocessing step for quantitative analysis of hyperspectral remote sensing imagery. While deep learning-based methods have achieved remarkable progress, three fundamental challenges remain: (i) reliance on a single shared spatial prior that cannot decouple the heterogeneous spatial patterns of different land covers; (ii) the lack of synergy in jointly optimizing endmember extraction and abundance estimation; (iii) the poor robustness of unsupervised training to complex mixtures, noise, and class imbalance. To address these issues, we propose a novel unsupervised unmixing framework that integrates adaptive orthogonal multi-faceted graph representation with curriculum learning. Specifically, we design an Adaptive Orthogonal Multi-Faceted Graph Generator (AOMFG) to learn a set of independent orthogonal graph structures, achieving spatially informed decoupling of land cover patterns. Then, a dual-branch collaborative optimization network is constructed: a Graph Convolutional Network (GCN) branch that incorporates the learned spatial topological priors for abundance estimation, and a 1D Convolutional Neural Network (1DCNN) branch that employs a query-attention mechanism to adaptively aggregate pure spectral features for endmember extraction. Finally, we introduce a three-stage curriculum learning strategy that progressively fine-tunes the model, which significantly enhances its performance. Extensive experiments on three widely used real-world benchmark datasets demonstrate that our proposed framework consistently outperforms state-of-the-art methods in both endmember extraction and abundance estimation accuracy. Comprehensive ablation studies, parameter sensitivity analysis, and noise robustness tests further validate the effectiveness of each core component.

Research on tourism resource demand offers critical decision support for the protection, development, and marketing of tourism resources. It also improves personalized experiences and satisfaction for tourists, thus fostering the advancement of the tourism industry into broader and higher realms. It also improves personalized experiences and satisfaction for tourists, thus fostering the advancement of the tourism industry into broader and higher realms. The objective of this study is to extract characteristics of 3A-level and above scenic spots nationwide, facilitating the integration and utilization of tourism resources in the country. The objective of this study is to extract characteristics of 3A-level and above scenic spots nationwide, facilitating the integration and utilization of tourism information. This facilitates the automation and efficiency of tourism resource classification and provides suggestions for improving services at these scenic areas. In response to the abundant resources of major scenic areas across the country, a new approach has been developed. In response to the abundant resources of major scenic areas across the country, this study introduces a hierarchical multi-label classification model for tourism resources. tourism resource classification theme system issued by the Ministry of Culture and Tourism, and leveraging FastText for pre-training on scenic area introductory texts, this research combines the advantages of the hierarchical multi-label classification model with the theme system of the Ministry of Culture and Tourism. introductory texts, this research combines the traditional LSTM model with an attention-based Transformer model. Additionally, a Graph-Convolutional Network (GCN) is used to classify tourism resources. Convolutional Network (GCN) is employed as a hierarchical structure-aware encoder to construct the MiLCT, a hierarchical multi-label classification model, enabling sophisticated multi-label classification to be applied to the text. model, enabling sophisticated multi-label classification of tourism scenic area resource data. Experimental comparisons demonstrate that, with increasing classification levels, the proposed model outperforms those lacking GCN and Transformer components in terms of micro-Precision, micro-Recision, micro-Recision, and micro-Recision. micro-Precision, micro-Recall, and micro-F1 scores, this indicates that the hierarchical structural information of the model can significantly enhance its performance. In comparison to the hierarchical multi-label correlation model, the proposed model demonstrates enhanced performance across the evaluated metrics, indicating its efficacy in integrating multimodal features and providing more comprehensive and accurate data characterization.

Hierarchical multilabel classification (HMC) assigns multiple labels to each instance with the labels organized under hierarchical relations. In ship classification in remote sensing images, depending on the expert knowledge and image quality, the same type of ships in different remote sensing images may be annotated with different class labels from coarse to fine levels such as merchant ship (MS) or container ship (CTS). In this article, we propose a novel deep network with two output channels and their associated loss functions to learn an HMC classifier using samples labeled at different levels in the hierarchy. In the proposed network, a hierarchy and exclusion (HEX) graph is introduced to model the label hierarchy, which satisfies hierarchical constraints by encoding semantic relations between any two labels. The output nodes of the first channel are organized according to the HEX graph, and its corresponding probabilistic classification loss is built to reflect the hierarchical structure of the HEX graph. On the other hand, the output nodes of the second channel only represent the finest grained (last level in the hierarchy) classes, and its multiclass cross-entropy loss is designed to enhance the discriminative power of the HMC classifier on the last level labels, which is also compatible with constraints in the HEX graph. The combination of these two losses from two output channels can effectively transfer the hierarchical information of ship taxonomy during network training. Experimental results on two commonly used ship datasets demonstrate that the proposed method outperforms the state-of-the-art HMC approaches, and is especially advantageous when trained with fewer fine-grained samples.

Drainage network pattern recognition is a significant task with wide applications in geographic information mining, map cartography, water resources management, and urban planning. Accurate identification of spatial patterns in river networks can help us understand geographic phenomena, optimize map cartographic quality, assess water resource potential, and provide a scientific basis for urban development planning. However, river network pattern recognition still faces challenges due to the complexity and diversity of river networks. To address this issue, this study proposes a river network pattern recognition method based on graph convolutional networks (GCNs), aiming to achieve accurate classification of different river network patterns. We utilize binary trees to construct a hierarchical tree structure based on river reaches and progressively determine the tree hierarchy by identifying the upstream and downstream relationships among river reaches. Based on this representation, input features for the graph convolutional model are extracted from both spatial and geometric perspectives. The effectiveness of the proposed method is validated through classification experiments on four types of vector river network data (dendritic, fan-shaped, trellis, and fan-shaped). The experimental results demonstrate that the proposed method can effectively classify vector river networks, providing strong support for research and applications in related fields.

Hierarchical multi-label text classification (HMTC) has become rather challenging when it requires handling large sets of closely related categories. We present a novel software that provides a hybrid embedding-based text representation for HMTC, shortened as HE-HMTC. It made full use of categories’ structure and their labels semantics to enrich the text representation, and therefore attempted to improve the classification performance of the text. In addition, HE-HMTC facilitates improving the accuracy of HMTC tasks. Moreover, our HE-HMTC can easily be generalized in other hierarchical classification tasks and achieve superior performance.

In this study, a hierarchical multi-label classification method called HFFNet-2d is proposed for the automatic classification of scanning electron microscope (SEM) images of metal failure. The method combines the advantages of convolutional neural networks (CNN) and Vision Transformers (ViT) to effectively realize hierarchical feature extraction and classification of SEM images of fracture morphologies, enabling accurate identification of metal failure mechanisms at different scales. The dataset of high-quality SEM images in this work is sourced from reputable materials science publications for its comprehensive coverage of various failure modes and its suitability for training and validating the hierarchical multi-label classification model. The HFFNet-2d model can achieve a high accuracy of 97.71% in the first-level classification and 92.62% in the second-level sub-category identification. This performance surpasses the human experts on the same task. To ensure that the model predictions are sufficiently reliable, a multi-level gradcam algorithm is also introduced for checking the regions of interest of the Hierarchical model at two levels and the comparisons are made with human experts. It is anticipated that the optimization and extension of HFFNet-2d are conducive in diverse material systems and application scenarios to accelerate the intelligent process of material development and failure analysis, ultimately supporting the design of reliable and high-performance engineering materials.