Wanrong Gu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Wanrong Gu has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Haiyan Wang
South China Agricultural University
3 shared publications Jianyu Li
South China Agricultural University
3 shared publications- Xianfen Xie
School of Economy, Jinan University, Guangzhou, China
3 shared publications - Yichen He
School of Computer Science and Engineering, South China University of Technology, Guangzhou, China
3 shared publications - Yijun Mao
College of Mathematics and Informatics, South China Agricultural University, Guangzhou 510642, China
3 shared publications - Guang-Yu Zhang
South China Agricultural University
2 shared publications
Latest Publications
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28, 15853-15865
One-Step Anchor-Guided Multi-View Clustering via Tensor-Consistent Graph Factorization
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28, 15853-15865
One-Step Anchor-Guided Multi-View Clustering via Tensor-Consistent Graph Factorization
- 25 June 2025
- Published by Springer Nature
- p. 298-312
SPANet: Scalable Pose Aggregation Network For Macaque Pose Estimation
- 25 June 2025
- Published by Springer Nature
- p. 298-312
SPANet: Scalable Pose Aggregation Network For Macaque Pose Estimation
- 9 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Emerging Topics in Computational Intelligence
- Vol. 9 (4) , 2952-2964
Efficient Multi-View Clustering via Essential Tensorized Bipartite Graph Learning
Multi-view spectral clustering has garnered significant attention for its capacity to integrate intrinsic feature information from multiple perspectives, resulting in improved performance. However, the oversight of inter-view correlations has led to suboptimal outcomes. Furthermore, the conventional method of constructing an $N \times N$ graph in multi-view clustering imposes a substantial time burden when dealing with large-scale scenarios. To address these challenges, this paper presents an efficient multi-view clustering approach via Essential Tensorized Bipartite Graph Learning (ETBGL). Specifically, ETBGL utilizes the low-rank tensor Schatten $p$-norm to capture inter-view similarity, effectively capturing high-order correlation information embedded in multiple views. Simultaneously, by incorporating bipartite graph learning, ETBGL efficiently mitigates the computational demands and spatial complexity associated with tensor operations. Additionally, we introduce the $\ell _{2,1}$-norm of tensor as a sparse penalty to the error term, with the aim of filtering out noise and preserving shared information, thus enhancing clustering robustness. We solve our objective by an efficient algorithm that is time-economical and has good convergence. Comprehensive evaluations on diverse datasets demonstrate the exceptional performance of our proposed model.
- 9 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Emerging Topics in Computational Intelligence
- Vol. 9 (4) , 2952-2964
Efficient Multi-View Clustering via Essential Tensorized Bipartite Graph Learning
Multi-view spectral clustering has garnered significant attention for its capacity to integrate intrinsic feature information from multiple perspectives, resulting in improved performance. However, the oversight of inter-view correlations has led to suboptimal outcomes. Furthermore, the conventional method of constructing an $N \times N$ graph in multi-view clustering imposes a substantial time burden when dealing with large-scale scenarios. To address these challenges, this paper presents an efficient multi-view clustering approach via Essential Tensorized Bipartite Graph Learning (ETBGL). Specifically, ETBGL utilizes the low-rank tensor Schatten $p$-norm to capture inter-view similarity, effectively capturing high-order correlation information embedded in multiple views. Simultaneously, by incorporating bipartite graph learning, ETBGL efficiently mitigates the computational demands and spatial complexity associated with tensor operations. Additionally, we introduce the $\ell _{2,1}$-norm of tensor as a sparse penalty to the error term, with the aim of filtering out noise and preserving shared information, thus enhancing clustering robustness. We solve our objective by an efficient algorithm that is time-economical and has good convergence. Comprehensive evaluations on diverse datasets demonstrate the exceptional performance of our proposed model.
- 12 October 2023
- Published by Springer Nature
- p. 142-148
Cloud, Edge, and Fog Computing Technologies in Agriculture
- 12 October 2023
- Published by Springer Nature
- p. 142-148
Cloud, Edge, and Fog Computing Technologies in Agriculture
- 3 February 2023
- Published by Springer Nature
- p. 1-7
Cloud, Edge, and Fog Computing Technologies in Agriculture
- 3 February 2023
- Published by Springer Nature
- p. 1-7
Cloud, Edge, and Fog Computing Technologies in Agriculture
- 5 January 2023
- Published by Springer Nature
- p. 1-7
“Cloud, Edge, and Fog Computing Technologies” in Agriculture
- 5 January 2023
- Published by Springer Nature
- p. 1-7
“Cloud, Edge, and Fog Computing Technologies” in Agriculture
- 11 July 2022
- Published by Springer Nature in Journal of Intelligent Information Systems
- Vol. 59 (3) , 801-823
An improved recommendation based on graph convolutional network
- 11 July 2022
- Published by Springer Nature in Journal of Intelligent Information Systems
- Vol. 59 (3) , 801-823
An improved recommendation based on graph convolutional network
- Open Access
- 15 June 2022
- Published by Springer Nature in Research Square
An Improved Recommendation Based on Graph Convolutional Network
Graph convolutional network is a recently developed artificial neural network method commonly used in recommendation system research. This paper points out three shortcomings of existing recommendation systems based on the graph convolutional network. 1. Existing models that take the one-hot encoding based on node ordinal numbers in the graph or encoding based on original entity attributes as input may not fully utilize the information carried by the attribute interactions. 2. Previous models update the node embeddings only by the first-order neighbors in the graph convolution layer, which is easily affected by noise. 3. Existing models do not take into account differences in user opinions. We propose an improved graph convolutional network-based collaborative filtering model to address these drawbacks. We identify inner and cross interaction between user attributes and item attributes, and then we take the vector representations of aggregated attributes graph as input. In the convolutional layer, we aggregate the second-order collaborative signals and incorporate the different user opinions. The experiments on three public datasets show that our model outperforms state-of-the-art models. Compared with baselines, it shows an improved performance (2.1% ∼ 4.3%).
- 15 June 2022
- Published by Springer Nature in Research Square
Open AccessAn Improved Recommendation Based on Graph Convolutional Network
Graph convolutional network is a recently developed artificial neural network method commonly used in recommendation system research. This paper points out three shortcomings of existing recommendation systems based on the graph convolutional network. 1. Existing models that take the one-hot encoding based on node ordinal numbers in the graph or encoding based on original entity attributes as input may not fully utilize the information carried by the attribute interactions. 2. Previous models update the node embeddings only by the first-order neighbors in the graph convolution layer, which is easily affected by noise. 3. Existing models do not take into account differences in user opinions. We propose an improved graph convolutional network-based collaborative filtering model to address these drawbacks. We identify inner and cross interaction between user attributes and item attributes, and then we take the vector representations of aggregated attributes graph as input. In the convolutional layer, we aggregate the second-order collaborative signals and incorporate the different user opinions. The experiments on three public datasets show that our model outperforms state-of-the-art models. Compared with baselines, it shows an improved performance (2.1% ∼ 4.3%).
- 19 April 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 32 (9) , 4267-4276
Adaptive Dropout Method Based on Biological Principles
Dropout is one of the most widely used methods to avoid overfitting neural networks. However, it rigidly and randomly activates neurons according to a fixed probability, which is not consistent with the activation mode of neurons in the human cerebral cortex. Inspired by gene theory and the activation mechanism of brain neurons, we propose a more intelligent adaptive dropout, in which a variational self-encoder (VAE) overlaps to an existing neural network to regularize its hidden neurons by adaptively setting activities to zero. Through alternating iterative training, the discarding probability of each hidden neuron can be learned according to the weights and thus effectively avoid the shortcomings of the standard dropout method. The experimental results in multiple data sets illustrate that this method can better suppress overfitting in various neural networks than can the standard dropout. Additionally, this adaptive dropout technique can reduce the number of neurons and improve training efficiency.
- 19 April 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 32 (9) , 4267-4276
Adaptive Dropout Method Based on Biological Principles
Dropout is one of the most widely used methods to avoid overfitting neural networks. However, it rigidly and randomly activates neurons according to a fixed probability, which is not consistent with the activation mode of neurons in the human cerebral cortex. Inspired by gene theory and the activation mechanism of brain neurons, we propose a more intelligent adaptive dropout, in which a variational self-encoder (VAE) overlaps to an existing neural network to regularize its hidden neurons by adaptively setting activities to zero. Through alternating iterative training, the discarding probability of each hidden neuron can be learned according to the weights and thus effectively avoid the shortcomings of the standard dropout method. The experimental results in multiple data sets illustrate that this method can better suppress overfitting in various neural networks than can the standard dropout. Additionally, this adaptive dropout technique can reduce the number of neurons and improve training efficiency.