Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Meixia Qu has a total of 38 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Towards Federated Long-Tailed Graph Learning: An energy-guided dual decoupling approach

    by Lianshuai Guo, Zhongzheng Yuan, Xunkai Li, Meixia Qu, Wenyu Wang

  • Generalized category discovery in federated graph learning

    by Zhongzheng Yuan, Lianshuai Guo, Xunkai Li, Wenyu Wang, Meixia Qu

  • Open Access

    Towards Federated Long-Tailed Graph Learning: An Energy-Guided Dual Decoupling Approach

    by Lianshuai Guo, Zhongzheng Yuan, Xunkai Li, Meixia Qu, Wenyu Wang

    Federated Graph Learning facilitates collaborative graph modeling across distributed clients while preserving data privacy.However, real-world data categories frequently exhibit long-tailed distributions. Such statistical scarcity severely degrades performance in two ways: it biases the global model toward majority classes, and it structurally isolates minority nodes by submerging them in heterophilic, head-dominated neighborhoods.While existing methods attempt topology-agnostic statistical compensations, they often fail under data scarcity.Instead of recovering tail nodes, they overfit the structural noise from adjacent dominant classes, leading to representation degradation.To address these limitations, we propose FedEPD, a framework built on a dual decoupling paradigm that separates topological purification from semantic recalibration.Specifically, FedEPD utilizes distribution-aware Dirichlet energy pruning to filter spatial heterophilic edges. It then overcomes Non-IID distribution shifts by extracting robust global prototypes from topologically central nodes, which are incorporated into local representations via a spatial low-pass prototype injection. Furthermore, a two-stage alternating optimization strategy strictly protects majority decision boundaries while improving minority accuracy.Extensive experiments demonstrate that FedEPD achieves state-of-the-art performance across diverse long-tailed benchmarks, yielding absolute improvements of up to 4.97\% in Accuracy and 5.48% in Macro-F1.

  • Open Access

    VDMS: An Improved Vision Transformer-Based Model for PM2.5 Concentration Prediction

    by Tong Zhao, Meixia Qu

    China’s accelerating industrialization has led to worsening air pollution, characterized by recurrent haze episodes. The accurate quantification of PM2.5 distribution is crucial for air quality assessment and public health management. Although traditional prediction models can effectively identify PM2.5 concentration fluctuations with moderate accuracy, their dependence relies heavily on extensive ground-based monitoring station data, limiting their applicability in areas with sparse monitoring coverage. To address this limitation, this study proposes a novel algorithm for high-precision PM2.5 concentration prediction, termed VDMS (Vision Transformer with DLSTM Multi-Head Self-Attention and Self-supervision). Based on the traditional Vision Transformer (ViT) architecture, VDMS incorporates a Double-Layered Long Short-Term Memory (DLSTM) network and a Multi-Head Self-Attention mechanism to enhance the model’s capacity to capture temporal sequence features and global dependencies. These enhancements contribute to greater stability and robustness in feature representation, ultimately improving prediction performance. Cross-validation experimental results show that the VDMS model outperforms benchmark models in PM2.5 concentration prediction tasks, achieving a coefficient of determination (R2) of 0.93, a root mean square error (RMSE) of 4.05 μg/m3, and a mean absolute error (MAE) of 3.23 μg/m3. Furthermore, experiments conducted in areas with sparse ground monitoring stations demonstrate that the model maintains high predictive accuracy, further validating its applicability and generalization capability in data-limited scenarios. Moreover, the VDMS model adopts a modular design, offering strong scalability that allows its architecture to be adjusted according to specific requirements. This adaptability renders it suitable for monitoring various atmospheric pollutants, providing essential technical support for precise environmental management and air quality forecasting.

  • Open Access

    VDMS: An Improved Vision Transformer-Based Model for PM2.5 Concentration Prediction

    by Tong Zhao, Meixia Qu

    China’s accelerating industrialization has led to worsening air pollution, characterized by recurrent haze episodes. Accurate quantification of PM2.5 distribution is crucial for air quality assessment and public health management. Although traditional prediction models can effectively identify PM2.5 concentration fluctuations with moderate accuracy, their dependence rely heavily on extensive ground-based monitoring station data, limiting their applicability in areas with sparse monitoring coverage. To address this limitation, this study proposes a novel algorithm for high-precision PM2.5 concentration prediction, termed VDMS (Vision Transformer with DLSTM Multi-Head Self-Attention and Self-supervision). Based on the traditional Vision Transformer (ViT) architecture, VDMS incorporates a Double-Layered Long Short-Term Memory (DLSTM) network and a Multi-Head Self-Attention mechanism to enhance the model’s capacity to capture temporal sequence features and global dependencies. These enhancements contribute to greater stability and robustness in feature representation, ultimately improving prediction performance. Cross-validation experimental results show that the VDMS model outperforms benchmark models in PM2.5 concentration prediction tasks, achieving a coefficient of determination (R²) of 0.93, a root mean square error (RMSE) of 4.05 µg/m³, and a mean absolute error (MAE) of 3.23 µg/m³. Furthermore, experiments conducted in areas with sparse ground monitoring stations demonstrate that the model maintains high predictive accuracy, further validating its applicability and generalization capability in data-limited scenarios. Moreover, the VDMS model adopts a modular design, offering strong scalability that allows its architecture to be adjusted according to specific requirements. This adaptability renders it suitable for monitoring various atmospheric pollutants, providing essential technical support for precise environmental management and air quality forecasting.

  • FedPPD: Towards effective subgraph federated learning via pseudo prototype distillation

    by Qi Lin, Jishuo Jia, Yinlin Zhu, Xunkai Li, Bin Jiang, Meixia Qu


  • Steel surface defect detection based on improved YOLOv8

    by Xin-Ya Lu, Mei-Xia Qu

    Addressing the issue of imbalance between detection accuracy and speed in current steel surface defect detection methods, we propose an improved YOLOv8-based algorithm, named YOLO-SSD, for steel surface defect detection. This algorithm replaces the downsampling module with a SPD-Conv module in the backbone network and introduces the CBAM attention module to enhance feature extraction capability and small object detection ability. Additionally, in the neck network, the C2f module is replaced with a C2f-Ghost module, which not only lightweightens the neck module but also improves the utilization of computational resources. Experimental results on the NEU-DET dataset demonstrate that compared to the original YOLOv8 algorithm, the average detection accuracy of the YOLO-SSD algorithm for steel surface defect detection has been improved by 2.8%, with a frame per second (FPS) reaching 96. Compared to current mainstream steel surface defect detection algorithms, the improved detection algorithm can enhance the detection accuracy of the defect detection model without compromising detection speed.


  • Effective Global Context Integration for Lightweight 3D Medical Image Segmentation

    by Qiang Qiao, Meixia Qu, Wenyu Wang, Bin Jiang, Qiang Guo

    Accurate and fast segmentation of 3D medical images is crucial in clinical analysis. CNNs struggle to capture long-range dependencies because of their inductive biases, whereas the Transformer can capture global features but faces a considerable computational burden. Thus, efficiently integrating global and detailed insights is key for precise segmentation. In this paper, we propose an effective and lightweight architecture named GCI-Net to address this issue. The key characteristic of GCI-Net is the global-guided feature enhancement strategy (GFES), which integrates the global context and facilitates the learning of local information; 3D convolutional attention, which captures long-range dependencies; and a progressive downsampling module, which perceives detailed information better. The GFES can capture the local range of information through global-guided feature fusion and global–local contrastive loss. All these designs collectively contribute to lower computational complexity and reliable performance improvements. The proposed model is trained and tested on four public datasets, namely MSD Brain Tumor, ACDC, BraTS2021, and MSD Lung. The experimental results show that, compared with several recent SOTA methods, our GCI-Net achieves superior computational efficiency with comparable or even better segmentation performance. The code is available at https://github.com/qintianjian-lab/GCI-Net.