Chun-Yang Zhang

Chun-Yang Zhang

Auto-generated profile, based on publicly available information

Chun-Yang Zhang

College of Computer and Data Science, Fuzhou University, Fuzhou, China

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
27 February 2019 in IEEE Transactions on Fuzzy Systems
Verified
Journal Article
Closed access
SFShuang Feng
Shuang Feng
CCC.L. Philip Chen
C.L. Philip Chen
CZChun-Yang Zhang
Chun-Yang Zhang
We establish a fuzzy deep model called the fuzzy deep belief net (FDBN) based on fuzzy restricted Boltzmann machines (FRBMs) due to their excellent generative and discriminative properties. The learning procedure of an FDBN is divided into a pretraining phase and a subsequent fine-tuning phase. In the pretraining phase, a group of FRBMs is trained in a greedy layerwise way: the first FRBM is trained by original samples, and the average values of the left and right probabilities produced by its hidden units are treated as the training data for subsequent FRBMs. The resulting FDBN is either a generative or a discriminative model depending on the choice of training a generative or a discriminative type of FRBM on top. Then, a hybrid learning approach is proposed to fine-tune this novel fuzzy deep model: the well pretrained fuzzy parameters are first defuzzified, and the FDBN with defuzzified parameters is fine-tuned by the wake-sleep or stochastic gradient descent algorithm. This hybrid strategy not only avoids learning an intractable fuzzy neural network, but also greatly improves the classification capability of the FDBN. The experimental results on MNIST, NORB, and 15 Scene databases indicate that the FDBN with the hybrid learning approach can handle high-dimensional raw images directly. It inherits the fine nature of the FRBM and outperforms some state-of-the-art discriminative models in classification accuracy. Moreover, it shows better capability of robustness than a deep belief net when encountering noisy data.

17 August 2022 in IEEE Transactions on Systems, Man, and Cybernetics: Systems
Verified
Journal Article
Closed access
CZChun-Yang Zhang
Chun-Yang Zhang
ZYZhi-Liang Yao
Zhi-Liang Yao
HYHong-Yu Yao
Hong-Yu Yao
FHFeng Huang
Feng Huang
CCC.L. Philip Chen
C.L. Philip Chen
A large number of real-world systems generate graphs that are structured data aligned with nodes and edges. Graphs are usually dynamic in many scenarios, where nodes or edges keep evolving over time. Recently, graph representation learning (GRL) has received great success in network analysis, which aims to produce informative and representative features or low-dimensional embeddings by exploring node attributes and network topology. Most state-of-the-art models for dynamic GRL are composed of a static representation learning model and a recurrent neural network (RNN). The former generates the representations of a graph or nodes from one static graph at a discrete time step, while the latter captures the temporal correlation between adjacent graphs. However, the two-stage design ignores the temporal dynamics between contiguous graphs during the learning processing of graph representations. To alleviate this problem, this article proposes a representation learning model for dynamic graphs, called DynGNN. Differently, it is a single-stage model that embeds an RNN into a graph neural network to produce better representations in a compact form. This takes the fusion of temporal and topology correlations into account from low-level to high-level feature learning, enabling the model to capture more fine-grained evolving patterns. From the experimental results on both synthetic and real-world networks, the proposed DynGNN yields significant improvements in multiple tasks compared to the state-of-the-art counterparts.

6 March 2023 in IEEE Transactions on Fuzzy Systems
Verified
Journal Article
Closed access
CZChun-Yang Zhang
Chun-Yang Zhang
YLYue-Na Lin
Yue-Na Lin
CCC.L. Philip Chen
C.L. Philip Chen
HYHong-Yu Yao
Hong-Yu Yao
HCHai-Chun Cai
Hai-Chun Cai
WFWu-Peng Fang
Wu-Peng Fang
Recent years have witnessed a drastic surge in graph representation learning, which usually produces low-dimensional and crisp representations from graph topology and high-dimensional node attributes. Nevertheless, a crisp representation of a node or graph actually conceals the uncertainty and interpretability of features. In citation networks, for example, the reference between two papers is always involved with fuzziness denoting the correlation degrees, that is, one connection may simultaneously belong to strong and weak references in different beliefs. The uncertainty in node connections and attributes inspires us to delve into fuzzy representations. This paper, for the first time, proposes an unsupervised fuzzy representation learning model for graphs and networks to improve their expressiveness by making crisp representations fuzzy. Specifically, we develop a fuzzy graph convolution neural network (FGCNN), which could aggregate high-level fuzzy features, leveraging fuzzy logic to fully excavate feature-level uncertainties, and finally generate fuzzy representations. The corresponding hierarchical model composed of multiple FGCNNs, called deep fuzzy graph convolution neural network (DFGCNN), is able to generate fuzzy node representations which are more expressive than crisp ones. Experimental results of multiple network analysis tasks validate that the proposed fuzzy representation models have strong competitiveness against the state-of-the-art baselines over several real-world datasets.

23 August 2023 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
FLFeng-Jie Li
Feng-Jie Li
CZChun-Yang Zhang
Chun-Yang Zhang
CCC.L. Philip Chen
C.L. Philip Chen
Accurate prediction of vehicle trajectories is crucial to the safety and comfort of autonomous vehicles. Although several graph-based models have exhibited substantial progress in acquiring spatiotemporal dependencies among vehicles in the driving environment, the potential for additional exploration in this domain persists. The main reason is that they concentrated on independently capturing the spatial relations and temporal dependencies, neglecting to incorporate the temporal feature into the spatial feature for co-training, which limits their ability to yield satisfactory predictive accuracy. Typically, spatial and temporal correlations are coupled and should be modeled jointly. Inspired by this, a novel dynamic graph neural network with spatial-temporal synchronization (STS-DGNN) for vehicle trajectory prediction is proposed, which constructs the driving scene as dynamic graphs and can jointly extract spatial-temporal features. Specifically, low-order and high-order dynamics of vehicle trajectories are considered collaboratively in a one-stage framework rather than independently modeling the spatial relationship and temporal correlations of vehicles in two-stage models. The proposed model also considers the dynamic nature of graph sequence by utilizing gate recurrent unit (GRU) to update the graph neural network (GNN) parameters dynamically. The spatial-temporal features are subsequently conveyed to convolutional neural networks (CNN) and processed by a multi-layer perceptron (MLP) to generate the ultimate trajectories. Finally, to illustrate the effectiveness of the STS-DGNN model, the model is assessed on three well-known datasets, namely highD, EWAP and UCY. The results confirm that our model performs better at making predictions than cutting-edge models. The visualization results intuitively explain that our method can extract sophisticated and subtle multi-vehicle interactions, resulting in accurate predictions.

9 March 2020 in IEEE Transactions on Cybernetics
Verified
Journal Article
Closed access
CZChun-Yang Zhang
Chun-Yang Zhang
YXYong-Yi Xiao
Yong-Yi Xiao
JLJin-Cheng Lin
Jin-Cheng Lin
CCC.L. Philip Chen
C.L. Philip Chen
WLWenxi Liu
Wenxi Liu
YTYu-Hong Tong
Yu-Hong Tong
Data representation learning is one of the most important problems in machine learning. Unsupervised representation learning becomes meritorious as it has no necessity of label information with observed data. Due to the highly time-consuming learning of deep-learning models, there are many machine-learning models directly adapting well-trained deep models that are obtained in a supervised and end-to-end manner as feature abstractors to distinct problems. However, it is obvious that different machine-learning tasks require disparate representation of original input data. Taking human action recognition as an example, it is well known that human actions in a video sequence are 3-D signals containing both visual appearance and motion dynamics of humans and objects. Therefore, the data representation approaches with the capabilities to capture both spatial and temporal correlations in videos are meaningful. Most of the existing human motion recognition models build classifiers based on deep-learning structures such as deep convolutional networks. These models require a large quantity of training videos with annotations. Meanwhile, these supervised models cannot recognize samples from the distinct dataset without retraining. In this article, we propose a new 3-D deconvolutional network (3DDN) for representation learning of high-dimensional video data, in which the high-level features are obtained through the optimization approach. The proposed 3DDN decomposes the video frames into spatiotemporal features under a sparse constraint in an unsupervised way. In addition, it also can be regarded as a building block to develop deep architectures by stacking. The high-level representation of input sequential data can be used in multiple downstream machine-learning tasks, we evaluate the proposed 3DDN and its deep models in human action recognition. The experimental results from three datasets: 1) KTH data; 2) HMDB-51; and 3) UCF-101, demonstrate that the proposed 3DDN is an alternative approach to feedforward convolutional neural networks (CNNs), that attains comparable results.

25 June 2024 in IEEE Transactions on Fuzzy Systems
Verified
Journal Article
Closed access
YLYue-Na Lin
Yue-Na Lin
HCHai-Chun Cai
Hai-Chun Cai
CZChun-Yang Zhang
Chun-Yang Zhang
HYHong-Yu Yao
Hong-Yu Yao
CCC.L. Philip Chen
C.L. Philip Chen
Graph representation learning (GRL) focuses on abstracting critical information from raw graphs. Unfortunately, there always exist various kinds of uncertainties such as attribute noise and network topology corruption in raw graphs. Under the message passing mechanism, these uncertainties are likely to spread throughout the whole graph. Matters like these would induce deep graph models into producing uncertain representations and restrict representation expressiveness. Considering this, we propose a pioneering framework to defend graph uncertainties by improving the robustness and capability of graph neural networks (GNNs). In our framework, we consider that weights and biases are all fuzzy numbers, thus generating representations to assimilate graph uncertainties which are finally released by defuzzification. To describe the process of the framework, in this paper, a graph convolutional network (GCN) is employed to construct a robust graph model, called FuzzyGCN. To verify the effectiveness of FuzzyGCN, it is trained in both supervised and unsupervised ways. In the supervised setting, we find that FuzzyGCN has stronger power and is more immune to data uncertainties when compared with various classical and robust GNNs. In the unsupervised setting, FuzzyGCN surpasses many state-of-the-art models in node classification and community detection over several real-world datasets.