Senyu Hou
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Senyu Hou has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Gaoxia Jiang
School of Computer and Information Technology, Shanxi University, Taiyuan, China
4 shared publications - Wenjian Wang
Shanxi University
4 shared publications - Yaqing Guo
School of Computer and Information Technology, Shanxi University, Taiyuan, China
3 shared publications - Fan Lei
School of Computer and Information Technology, Shanxi University, Taiyuan, Shanxi, China
1 shared publication - Hang Xu
School of Computer and Information Technology, Shanxi University, Taiyuan, Shanxi, China
1 shared publication - Lingxuan Cui
School of Computer and Information Technology, Shanxi University, Taiyuan, Shanxi, China
1 shared publication
Latest Publications
- 12 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (3) , 1527-1540
Class-Aware Multi-Granularity Co-Diffusion Models for Learning With Noisy Labels on Imbalanced Datasets
Data quality is essential for the performance of deep neural networks in various fields. However, label noise and class imbalance are common data issues, which cause deep learning models to overfit in real-world scenarios. Recent research solves the learning with noisy labels (LNL) problem by employing label correction or loss adjustment methods, which often rely on uncertainty estimation. Unfortunately, these methods usually do not work well with imbalanced datasets. To address both noisy and imbalanced data biases, we analyze the limitations of current discriminative models in uncertainty estimation, and propose Class-aware Multi-granularity Co-Diffusion models (CaMCoD), which leverage a generative uncertainty and inconsistency loss adjustment method to generate labels more robustly. Specifically, we reframe the LNL problem as a robust diffusion-generative process, i.e., labels are generated by gradually refining an initial random guess. First, we use coarse-grained uncertainty from the diffusion model to achieve more accurate confidence estimates. This will guide the model to generate correct labels on a broader level. Then, we leverage the fine-grained inconsistency of co-diffusion models during reverse denoising to determine the learnable weight for each sample, which can mitigate the risk of the model overfitting to noisy samples. Finally, we apply class-aware loss adjustments to reduce data bias caused by class imbalance. Experiments on both synthetic and real-world datasets demonstrate that our method perform well in imbalanced and noisy scenarios.
- 12 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (3) , 1527-1540
Class-Aware Multi-Granularity Co-Diffusion Models for Learning With Noisy Labels on Imbalanced Datasets
Data quality is essential for the performance of deep neural networks in various fields. However, label noise and class imbalance are common data issues, which cause deep learning models to overfit in real-world scenarios. Recent research solves the learning with noisy labels (LNL) problem by employing label correction or loss adjustment methods, which often rely on uncertainty estimation. Unfortunately, these methods usually do not work well with imbalanced datasets. To address both noisy and imbalanced data biases, we analyze the limitations of current discriminative models in uncertainty estimation, and propose Class-aware Multi-granularity Co-Diffusion models (CaMCoD), which leverage a generative uncertainty and inconsistency loss adjustment method to generate labels more robustly. Specifically, we reframe the LNL problem as a robust diffusion-generative process, i.e., labels are generated by gradually refining an initial random guess. First, we use coarse-grained uncertainty from the diffusion model to achieve more accurate confidence estimates. This will guide the model to generate correct labels on a broader level. Then, we leverage the fine-grained inconsistency of co-diffusion models during reverse denoising to determine the learnable weight for each sample, which can mitigate the risk of the model overfitting to noisy samples. Finally, we apply class-aware loss adjustments to reduce data bias caused by class imbalance. Experiments on both synthetic and real-world datasets demonstrate that our method perform well in imbalanced and noisy scenarios.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (9) , 1-14
A Dual Correction Guarantee Mechanism for Numerical Label Noise
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 38 (9) , 1-14
A Dual Correction Guarantee Mechanism for Numerical Label Noise
- 5 July 2025
- Published by Elsevier in Neural Networks
- Vol. 191, 107827
Outlier-trimmed dual-interval smoothing loss for sample selection in learning with noisy labels
- 5 July 2025
- Published by Elsevier in Neural Networks
- Vol. 191, 107827
Outlier-trimmed dual-interval smoothing loss for sample selection in learning with noisy labels