Xuegang Hu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Xuegang Hu has a total of 131 co-authors. Here are the top co-authors by number of shared publications:
- Peipei Li
School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China
15 shared publications - Chenyang Bu
Key Laboratory of Knowledge Engineering with Big Data (the Ministry of Education of China), Hefei University of Technology, Hefei, Anhui, China
10 shared publications - Yuhong Zhang
Key Laboratory of Knowledge Engineering with Big Data (the Ministry of Education of China), Hefei University of Technology, Hefei, China and School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China
10 shared publications - Fei Liu
Hefei University of Technology
6 shared publications - Xindong Wu
Hefei University of Technology
6 shared publications - Kui Yu
School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, Anhui, China
5 shared publications
Latest Publications
- 24 July 2026
- Published by Elsevier in Bioorganic Chemistry
- Vol. 181, 110258
HSimGCDA: A novel higher-order similarity graph representation learning method for identifying CircRNA-disease associations
- 24 July 2026
- Published by Elsevier in Bioorganic Chemistry
- Vol. 181, 110258
HSimGCDA: A novel higher-order similarity graph representation learning method for identifying CircRNA-disease associations
- Open Access
- 3 June 2026
- Published by Elsevier in SSRN Electronic Journal
HSimGCDA: A Novel Higher-Order Similarity Graph Representation Learning Method for Identifying CircRNA-Disease Associations
Circular RNAs (circRNAs) have gained recognition for their critical roles in various biological processes and are increasingly viewed as promising candidates for use in disease diagnosis and treatment strategies for complex human diseases. Despite advances in computational methods for predicting circRNA-disease associations (CDAs), existing models often fail to effectively capture both similarity metrics and higher-order mixed neighbourhood information simultaneously in bio-graph networks, leading to suboptimal prediction performance. In this study, we present HSimGCDA, an enhanced graph convolutional network that leverages higher-order similarity measures to improve the prediction of CDAs. Specifically, our approach first constructs multi-similarity graph networks that integrate diverse data features of circRNAs and diseases. We then implement a higher-order similarity strategy that effectively aggregates the higher-order similarity information between nodes and their remote neighbors, thus enriching the topological information of the nodes and revealing potential features brought about by different neighboring nodes. Ultimately, a multilayer perceptron algorithm is utilized to accurately infer likely CDAs. The experimental results indicated that HSimGCDA demonstrated excellent competitiveness on the benchmark CircR2Disease dataset, achieving a prediction accuracy of 95.93% and an AUC score of 98.74%. Additionally, the ablation experiments further validated the effectiveness of the improved HSimGCDA model. Furthermore, case studies on gastric and breast cancers demonstrated that HSimGCDA successfully identified previously unrecognized circRNAs associated with these diseases. Collectively, these findings emphasize the potential of HSimGCDA as a practical tool for exploring CDA, thereby providing valuable insights into disease diagnosis and therapeutic development.
- 3 June 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessHSimGCDA: A Novel Higher-Order Similarity Graph Representation Learning Method for Identifying CircRNA-Disease Associations
Circular RNAs (circRNAs) have gained recognition for their critical roles in various biological processes and are increasingly viewed as promising candidates for use in disease diagnosis and treatment strategies for complex human diseases. Despite advances in computational methods for predicting circRNA-disease associations (CDAs), existing models often fail to effectively capture both similarity metrics and higher-order mixed neighbourhood information simultaneously in bio-graph networks, leading to suboptimal prediction performance. In this study, we present HSimGCDA, an enhanced graph convolutional network that leverages higher-order similarity measures to improve the prediction of CDAs. Specifically, our approach first constructs multi-similarity graph networks that integrate diverse data features of circRNAs and diseases. We then implement a higher-order similarity strategy that effectively aggregates the higher-order similarity information between nodes and their remote neighbors, thus enriching the topological information of the nodes and revealing potential features brought about by different neighboring nodes. Ultimately, a multilayer perceptron algorithm is utilized to accurately infer likely CDAs. The experimental results indicated that HSimGCDA demonstrated excellent competitiveness on the benchmark CircR2Disease dataset, achieving a prediction accuracy of 95.93% and an AUC score of 98.74%. Additionally, the ablation experiments further validated the effectiveness of the improved HSimGCDA model. Furthermore, case studies on gastric and breast cancers demonstrated that HSimGCDA successfully identified previously unrecognized circRNAs associated with these diseases. Collectively, these findings emphasize the potential of HSimGCDA as a practical tool for exploring CDA, thereby providing valuable insights into disease diagnosis and therapeutic development.
- Open Access
- 23 May 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 44 (5) , 1-23
MGCD: Multiple-Granularity Cognitive Diagnosis in Intelligent Education Systems
Cognitive diagnosis (CD) is an important task in the field of intelligent education, aiming to discover the proficiency of students on knowledge concepts with response logs. In applications, different users of the tutoring system demand for a diagnosis of knowledge concepts at different granularities. However, recent methods assume that the concepts are of the same granularity and use explicit correlations between same-granularity concepts to improve the diagnosis performance. If required for diagnosing multi-granularity concepts, these methods will face diminished performance or partial invalidation. To this end, we make the first attempt for multiple-granularity cognitive diagnosis, i.e., diagnosis on coarse- and fine-grained concepts simultaneously. Specifically, in a skillful way, the same-granularity correlations are captured and embedded into concept representations in view of concept semantics and cross-granularity correlations to model the proficiency influence between concepts implicitly. Then, the specific loss for single-granularity diagnosis and the general loss for the consistency of multi-granularity are designed to train the model jointly, achieving multiple-granularity diagnosis. Extensive experiments demonstrate that our method can achieve state-of-the-art accuracy on both coarse- and fine-grained concepts.
- 23 May 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 44 (5) , 1-23
Open AccessMGCD: Multiple-Granularity Cognitive Diagnosis in Intelligent Education Systems
Cognitive diagnosis (CD) is an important task in the field of intelligent education, aiming to discover the proficiency of students on knowledge concepts with response logs. In applications, different users of the tutoring system demand for a diagnosis of knowledge concepts at different granularities. However, recent methods assume that the concepts are of the same granularity and use explicit correlations between same-granularity concepts to improve the diagnosis performance. If required for diagnosing multi-granularity concepts, these methods will face diminished performance or partial invalidation. To this end, we make the first attempt for multiple-granularity cognitive diagnosis, i.e., diagnosis on coarse- and fine-grained concepts simultaneously. Specifically, in a skillful way, the same-granularity correlations are captured and embedded into concept representations in view of concept semantics and cross-granularity correlations to model the proficiency influence between concepts implicitly. Then, the specific loss for single-granularity diagnosis and the general loss for the consistency of multi-granularity are designed to train the model jointly, achieving multiple-granularity diagnosis. Extensive experiments demonstrate that our method can achieve state-of-the-art accuracy on both coarse- and fine-grained concepts.
- 12 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (8) , 5001-5014
DSPL: Dual-Space Prompt Learning With Context Bias Decoupling for Open Set Recognition
Open Set Recognition (OSR) aims to accurately classify known classes and effectively reject unknown classes in open-world scenarios, which is essential for building safe and reliable intelligent systems. Existing studies have shown that auxiliary data-based methods—utilizing outlier exposure or prompt-based guidance to strengthen OSR models—have achieved significant improvements. However, these methods are highly sensitive to the selection of data. Considering the demand for domain expertise and the cost implications, synthesizing data from known samples becomes a preferable alternative. To achieve performance on par with methods that incorporate auxiliary data, it is essential to address the following key challenges: (1) obtaining meaningful pseudo-unknown samples and prompts without manual intervention, and (2) establishing a reliable recognition mechanism during the inference phase. In this paper, we propose a novel Dual-Space Prompt Learning with Context Bias Decoupling (DSPL) method to address the above issues. Specifically, we symmetrically model the same number of unknown classes as known classes to achieve a balanced class distribution in the embedding space. Learnable textual templates are designed for both types of data. Meanwhile, boundary samples are synthesized and treated as pseudo-unknown samples by decoupling discriminative and co-occurring features. Additionally, unknown sample detection is performed by integrating the maximum posterior over known and unknown classes, thereby extending the advantages of symmetric modeling from the training phase to inference. Extensive experiments demonstrate that the proposed method DSPL achieves state-of-the-art performance compared with the most advanced OSR methods.
- 12 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (8) , 5001-5014
DSPL: Dual-Space Prompt Learning With Context Bias Decoupling for Open Set Recognition
Open Set Recognition (OSR) aims to accurately classify known classes and effectively reject unknown classes in open-world scenarios, which is essential for building safe and reliable intelligent systems. Existing studies have shown that auxiliary data-based methods—utilizing outlier exposure or prompt-based guidance to strengthen OSR models—have achieved significant improvements. However, these methods are highly sensitive to the selection of data. Considering the demand for domain expertise and the cost implications, synthesizing data from known samples becomes a preferable alternative. To achieve performance on par with methods that incorporate auxiliary data, it is essential to address the following key challenges: (1) obtaining meaningful pseudo-unknown samples and prompts without manual intervention, and (2) establishing a reliable recognition mechanism during the inference phase. In this paper, we propose a novel Dual-Space Prompt Learning with Context Bias Decoupling (DSPL) method to address the above issues. Specifically, we symmetrically model the same number of unknown classes as known classes to achieve a balanced class distribution in the embedding space. Learnable textual templates are designed for both types of data. Meanwhile, boundary samples are synthesized and treated as pseudo-unknown samples by decoupling discriminative and co-occurring features. Additionally, unknown sample detection is performed by integrating the maximum posterior over known and unknown classes, thereby extending the advantages of symmetric modeling from the training phase to inference. Extensive experiments demonstrate that the proposed method DSPL achieves state-of-the-art performance compared with the most advanced OSR methods.
- 25 February 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 339
Unified online weak multi-Label learning in drifting and imbalanced data streams
- 25 February 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 339
Unified online weak multi-Label learning in drifting and imbalanced data streams
- 10 December 2025
- Published by Elsevier in Pattern Recognition
- Vol. 173
Online multi-label classification under noisy and changing label distribution
- 10 December 2025
- Published by Elsevier in Pattern Recognition
- Vol. 173
Online multi-label classification under noisy and changing label distribution
- 2 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 37 (11) , 6680-6693
Semi-Supervised Short Text Stream Classification Based on Drift-Aware Incremental Deep Learning
Real-world applications have produced massive short text streams. Contrary to the traditional normal texts, they present the characteristics such as short length, only having few labeled data, high-velocity, high-volume and dynamic data distributions, which deteriorate the issues of data sparseness, label missing and concept drift. Obviously, it is a huge challenge for existing short text (stream) classification algorithms due to the poor effectiveness, where they always assume all short texts are completely labeled and little attention is paid on the concept drift issue hidden in short text streams. Therefore, we propose a novel semi-supervised short text steam classification method based on the drift-aware incremental deep learning ensemble model. Specifically, with the sliding window mechanism, we firstly fuse three types of statistical, semantic and structure information to solve the data sparseness issue. Secondly, a semi-supervised incremental deep learning ensemble model based on GCN and the refined LSTM is developed to adapt to the high-volume, high-velocity and label missing short text streams. Thirdly, a label-probability distribution based concept drift detector is introduced to distinguish concept drifts. Finally, as compared with eleven well-known classification methods, extensive experiments demonstrate the effectiveness of the proposed method in the handling of short text streams with limited labeled data.
- 2 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 37 (11) , 6680-6693
Semi-Supervised Short Text Stream Classification Based on Drift-Aware Incremental Deep Learning
Real-world applications have produced massive short text streams. Contrary to the traditional normal texts, they present the characteristics such as short length, only having few labeled data, high-velocity, high-volume and dynamic data distributions, which deteriorate the issues of data sparseness, label missing and concept drift. Obviously, it is a huge challenge for existing short text (stream) classification algorithms due to the poor effectiveness, where they always assume all short texts are completely labeled and little attention is paid on the concept drift issue hidden in short text streams. Therefore, we propose a novel semi-supervised short text steam classification method based on the drift-aware incremental deep learning ensemble model. Specifically, with the sliding window mechanism, we firstly fuse three types of statistical, semantic and structure information to solve the data sparseness issue. Secondly, a semi-supervised incremental deep learning ensemble model based on GCN and the refined LSTM is developed to adapt to the high-volume, high-velocity and label missing short text streams. Thirdly, a label-probability distribution based concept drift detector is introduced to distinguish concept drifts. Finally, as compared with eleven well-known classification methods, extensive experiments demonstrate the effectiveness of the proposed method in the handling of short text streams with limited labeled data.
- 18 June 2025
- Published by Springer Nature in Applied Intelligence
- Vol. 55 (10) , 1-14
Multi-granularity decision information integration network for hierarchical classification via local and global constraints
- 18 June 2025
- Published by Springer Nature in Applied Intelligence
- Vol. 55 (10) , 1-14
Multi-granularity decision information integration network for hierarchical classification via local and global constraints
- 6 May 2025
- Published by Springer Nature
- p. 363-378
Enhancing Continuous Cognitive Diagnosis with Fuzzy Strategy-Based Hybrid Genetic Algorithm
- 6 May 2025
- Published by Springer Nature
- p. 363-378
Enhancing Continuous Cognitive Diagnosis with Fuzzy Strategy-Based Hybrid Genetic Algorithm
- 22 January 2025
- Published by Springer Nature in Journal of Imaging Informatics in Medicine
- Vol. 38 (5) , 3221-3234
Semi-Supervised Medical Image Segmentation Based on Frequency Domain Aware Stable Consistency Regularization
With the advancement of deep learning models nowadays, they have successfully applied in the semi-supervised medical image segmentation where there are few annotated medical images and a large number of unlabeled ones. A representative approach in this regard is the semi-supervised method based on consistency regularization, which improves model training by imposing consistency constraints (perturbations) on unlabeled data. However, the perturbations in this kind of methods are often artificially designed, which may introduce biases unfavorable to the model learning in the handling of medical image segmentation. On the other hand, the majority of such methods often overlook the supervision in the Encoder stage of training and primarily focus on the outcomes in the later stages, potentially leading to chaotic learning in the initial phase and subsequently impacting the learning process of the model in the later stages. At the meanwhile, they miss the intrinsic spatial-frequency information of the images. Therefore, in this study, we propose a new semi-supervised medical image segmentation approach based on frequency domain aware stable consistency regularization. Specifically, to avoid the bias introduced by artificially setting perturbations, we first utilize the inherent frequency domain information of images, including both high and low frequencies, as the consistency constraint. Secondly, we incorporate supervision in the Encoder stage of model training to ensure that the model does not fail to learn due to the disruption of the original feature space caused by strong augmentation. Finally, extensive experimentation validates the effectiveness of our semi-supervised approach.
- 22 January 2025
- Published by Springer Nature in Journal of Imaging Informatics in Medicine
- Vol. 38 (5) , 3221-3234
Semi-Supervised Medical Image Segmentation Based on Frequency Domain Aware Stable Consistency Regularization
With the advancement of deep learning models nowadays, they have successfully applied in the semi-supervised medical image segmentation where there are few annotated medical images and a large number of unlabeled ones. A representative approach in this regard is the semi-supervised method based on consistency regularization, which improves model training by imposing consistency constraints (perturbations) on unlabeled data. However, the perturbations in this kind of methods are often artificially designed, which may introduce biases unfavorable to the model learning in the handling of medical image segmentation. On the other hand, the majority of such methods often overlook the supervision in the Encoder stage of training and primarily focus on the outcomes in the later stages, potentially leading to chaotic learning in the initial phase and subsequently impacting the learning process of the model in the later stages. At the meanwhile, they miss the intrinsic spatial-frequency information of the images. Therefore, in this study, we propose a new semi-supervised medical image segmentation approach based on frequency domain aware stable consistency regularization. Specifically, to avoid the bias introduced by artificially setting perturbations, we first utilize the inherent frequency domain information of images, including both high and low frequencies, as the consistency constraint. Secondly, we incorporate supervision in the Encoder stage of model training to ensure that the model does not fail to learn due to the disruption of the original feature space caused by strong augmentation. Finally, extensive experimentation validates the effectiveness of our semi-supervised approach.