Na Lu
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
Na Lu has a total of 71 co-authors. Here are the top co-authors by number of shared publications:
Hanxuan Wang
5 shared publications- Ruofan Yan
Systems Engineering Institute, School of Automation Science and Engineering, Xi'an Jiaotong University, People's Republic of China; Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University, Hong Kong Special Administrative Region
5 shared publications Xu Niu
5 shared publications- Xu Niu
Systems Engineering Institute, School of Automation Science and Engineering, Xi'an Jiaotong University, People's Republic of China
5 shared publications - Yaguo Lei
Key Laboratory of Education Ministry for Modern Design and Rotor-Bearing System, Xian Jiaotong University, Xian, China
4 shared publications Yuxuan Yan
4 shared publications
Latest Publications
- 20 March 2026
- Published by Elsevier in Pattern Recognition
- Vol. 179
Latent belief reinforcement learning for online motor imagery classification
- 20 March 2026
- Published by Elsevier in Pattern Recognition
- Vol. 179
Latent belief reinforcement learning for online motor imagery classification
- 23 January 2026
- Published by Springer Nature
- p. 33-46
SegCL: Segmented Reasoning with Global Visual-Audio Knowledge for Complex Long Video Understanding
- 23 January 2026
- Published by Springer Nature
- p. 33-46
SegCL: Segmented Reasoning with Global Visual-Audio Knowledge for Complex Long Video Understanding
- 13 November 2025
- Published by Elsevier in Applied Soft Computing
- Vol. 186
Self-organized phase-locked component pair learning in motor imagery classification
- 13 November 2025
- Published by Elsevier in Applied Soft Computing
- Vol. 186
Self-organized phase-locked component pair learning in motor imagery classification
- 26 June 2025
- Published by Elsevier in Applied Soft Computing
- Vol. 181
Multiple attention relation network for few-shot learning
- 26 June 2025
- Published by Elsevier in Applied Soft Computing
- Vol. 181
Multiple attention relation network for few-shot learning
- 15 June 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 292
Reinforcement learning based early classification framework for power transformer differential protection
- 15 June 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 292
Reinforcement learning based early classification framework for power transformer differential protection
- Open Access
Graph Probability Aggregation Clustering
Traditional clustering methods typically focus on either cluster-wise global clustering or point-wise local clustering to reveal the intrinsic structures in unlabeled data. Global clustering optimizes an objective function to explore the relationships between clusters, but this approach may inevitably lead to coarse partition. In contrast, local clustering heuristically groups data based on detailed point relationships, but it tends to be less coherence and efficient. To bridge the gap between these two concepts and utilize the strengths of both, we propose Graph Probability Aggregation Clustering (GPAC), a graph-based fuzzy clustering algorithm. GPAC unifies the global clustering objective function with a local clustering constraint. The entire GPAC framework is formulated as a multi-constrained optimization problem, which can be solved using the Lagrangian method. Through the optimization process, the probability of a sample belonging to a specific cluster is iteratively calculated by aggregating information from neighboring samples within the graph. We incorporate a hard assignment variable into the objective function to further improve the convergence and stability of optimization. Furthermore, to efficiently handle large-scale datasets, we introduce an acceleration program that reduces the computational complexity from quadratic to linear, ensuring scalability. Extensive experiments conducted on synthetic, real-world, and deep learning datasets demonstrate that GPAC not only exceeds existing state-of-the-art methods in clustering performance but also excels in computational efficiency, making it a powerful tool for complex clustering challenges.
Open AccessGraph Probability Aggregation Clustering
Traditional clustering methods typically focus on either cluster-wise global clustering or point-wise local clustering to reveal the intrinsic structures in unlabeled data. Global clustering optimizes an objective function to explore the relationships between clusters, but this approach may inevitably lead to coarse partition. In contrast, local clustering heuristically groups data based on detailed point relationships, but it tends to be less coherence and efficient. To bridge the gap between these two concepts and utilize the strengths of both, we propose Graph Probability Aggregation Clustering (GPAC), a graph-based fuzzy clustering algorithm. GPAC unifies the global clustering objective function with a local clustering constraint. The entire GPAC framework is formulated as a multi-constrained optimization problem, which can be solved using the Lagrangian method. Through the optimization process, the probability of a sample belonging to a specific cluster is iteratively calculated by aggregating information from neighboring samples within the graph. We incorporate a hard assignment variable into the objective function to further improve the convergence and stability of optimization. Furthermore, to efficiently handle large-scale datasets, we introduce an acceleration program that reduces the computational complexity from quadratic to linear, ensuring scalability. Extensive experiments conducted on synthetic, real-world, and deep learning datasets demonstrate that GPAC not only exceeds existing state-of-the-art methods in clustering performance but also excels in computational efficiency, making it a powerful tool for complex clustering challenges.
- Open Access
Set a Thief to Catch a Thief: Combating Label Noise through Noisy Meta Learning
Learning from noisy labels (LNL) aims to train high-performance deep models using noisy datasets. Meta learning based label correction methods have demonstrated remarkable performance in LNL by designing various meta label rectification tasks. However, extra clean validation set is a prerequisite for these methods to perform label correction, requiring extra labor and greatly limiting their practicality. To tackle this issue, we propose a novel noisy meta label correction framework STCT, which counterintuitively uses noisy data to correct label noise, borrowing the spirit in the saying ``Set a Thief to Catch a Thief''. The core idea of STCT is to leverage noisy data which is i.i.d. with the training data as a validation set to evaluate model performance and perform label correction in a meta learning framework, eliminating the need for extra clean data. By decoupling the complex bi-level optimization in meta learning into representation learning and label correction, STCT is solved through an alternating training strategy between noisy meta correction and semi-supervised representation learning. Extensive experiments on synthetic and real-world datasets demonstrate the outstanding performance of STCT, particularly in high noise rate scenarios. STCT achieves 96.9% label correction and 95.2% classification performance on CIFAR-10 with 80% symmetric noise, significantly surpassing the current state-of-the-art.
Open AccessSet a Thief to Catch a Thief: Combating Label Noise through Noisy Meta Learning
Learning from noisy labels (LNL) aims to train high-performance deep models using noisy datasets. Meta learning based label correction methods have demonstrated remarkable performance in LNL by designing various meta label rectification tasks. However, extra clean validation set is a prerequisite for these methods to perform label correction, requiring extra labor and greatly limiting their practicality. To tackle this issue, we propose a novel noisy meta label correction framework STCT, which counterintuitively uses noisy data to correct label noise, borrowing the spirit in the saying ``Set a Thief to Catch a Thief''. The core idea of STCT is to leverage noisy data which is i.i.d. with the training data as a validation set to evaluate model performance and perform label correction in a meta learning framework, eliminating the need for extra clean data. By decoupling the complex bi-level optimization in meta learning into representation learning and label correction, STCT is solved through an alternating training strategy between noisy meta correction and semi-supervised representation learning. Extensive experiments on synthetic and real-world datasets demonstrate the outstanding performance of STCT, particularly in high noise rate scenarios. STCT achieves 96.9% label correction and 95.2% classification performance on CIFAR-10 with 80% symmetric noise, significantly surpassing the current state-of-the-art.
- Open Access
- 9 January 2025
- Published by Elsevier in Neural Networks
- Vol. 184, 107127
A Fine-grained Hemispheric Asymmetry Network for accurate and interpretable EEG-based emotion classification
- 9 January 2025
- Published by Elsevier in Neural Networks
- Vol. 184, 107127
Open AccessA Fine-grained Hemispheric Asymmetry Network for accurate and interpretable EEG-based emotion classification
- 26 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 37 (3) , 1439-1454
Self-Correcting Clustering
The incorporation of target distribution significantly enhances the success of deep clustering. However, most of the related deep clustering methods suffer from two drawbacks: (1) manually-designed target distribution functions with uncertain performance and (2) cluster misassignment accumulation. To address these issues, a Self - C orrecting C lustering (Self-CC) framework is proposed. In Self-CC, a robust target distribution solver (RTDS) is designed to automatically predict the target distribution and alleviate the adverse influence of misassignments. Specifically, RTDS divides the high confidence samples selected according to the cluster assignments predicted by a clustering module into labeled samples with correct pseudo labels and unlabeled samples of possible misassignments by modeling its training loss distribution. With the divided data, RTDS can be trained in a semi-supervised way. The critical hyperparameter which controls the semi-supervised training process can be set adaptively by estimating the distribution property of misassignments in the pseudo-label space with the support of a theoretical analysis. The target distribution can be predicted by the well-trained RTDS automatically, optimizing the clustering module and correcting misassignments in the cluster assignments. The clustering module and RTDS mutually promote each other forming a positive feedback loop. Extensive experiments on four benchmark datasets demonstrate the effectiveness of the proposed Self-CC.
- 26 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 37 (3) , 1439-1454
Self-Correcting Clustering
The incorporation of target distribution significantly enhances the success of deep clustering. However, most of the related deep clustering methods suffer from two drawbacks: (1) manually-designed target distribution functions with uncertain performance and (2) cluster misassignment accumulation. To address these issues, a Self - C orrecting C lustering (Self-CC) framework is proposed. In Self-CC, a robust target distribution solver (RTDS) is designed to automatically predict the target distribution and alleviate the adverse influence of misassignments. Specifically, RTDS divides the high confidence samples selected according to the cluster assignments predicted by a clustering module into labeled samples with correct pseudo labels and unlabeled samples of possible misassignments by modeling its training loss distribution. With the divided data, RTDS can be trained in a semi-supervised way. The critical hyperparameter which controls the semi-supervised training process can be set adaptively by estimating the distribution property of misassignments in the pseudo-label space with the support of a theoretical analysis. The target distribution can be predicted by the well-trained RTDS automatically, optimizing the clustering module and correcting misassignments in the cluster assignments. The clustering module and RTDS mutually promote each other forming a positive feedback loop. Extensive experiments on four benchmark datasets demonstrate the effectiveness of the proposed Self-CC.