Query：
学者姓名：张春阳
Refining：
Year
Type
Indexed by
Source
Complex
Co-
Language
Clean All
Abstract ：
With the rise of contrastive learning, unsupervised graph representation learning (GRL) has shown strong competitiveness. However, existing graph contrastive models typically either focus on the local view of graphs or take simple considerations of both global and local views. This may cause these models to overemphasize the importance of individual nodes and their ego networks, or to result in poor learning of global knowledge and affect the learning of local views. Additionally, most GRL models pay attention to topological proximity, assuming that nodes that are closer in graph topology are more similar. However, in the real world, close nodes may be dissimilar, which makes the learned embeddings incorporate inappropriate messages and thus lack discrimination. To address these issues, we propose a novel unsupervised GRL model by contrasting cluster assignments, called graph representation learning model via contrasting cluster assignment (GRCCA). To comprehensively explore the global and local views, it combines multiview contrastive learning and clustering algorithms with an opposite augmentation strategy. It leverages clustering algorithms to capture fine-grained global information and explore potential relevance between nodes in different augmented perspectives while preserving high-quality global and local information through contrast between nodes and prototypes. The opposite augmentation strategy further enhances the contrast of both views, allowing the model to excavate more invariant features. Experimental results show that GRCCA has strong competitiveness compared to state-of-the-art models in different graph analysis tasks.
Keyword ：
Clustering algorithms Clustering algorithms Contrastive learning Contrastive learning graph data mining graph data mining graph representation learning (GRL) graph representation learning (GRL) Prototypes Prototypes Representation learning Representation learning Social networking (online) Social networking (online) Task analysis Task analysis Topology Topology unsupervised learning unsupervised learning Unsupervised learning Unsupervised learning
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhang, Chun-Yang , Yao, Hong-Yu , Chen, C. L. Philip et al. Graph Representation Learning via Contrasting Cluster Assignments [J]. | IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS , 2024 , 16 (3) : 912-922 . |
| MLA | Zhang, Chun-Yang et al. "Graph Representation Learning via Contrasting Cluster Assignments" . | IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS 16 . 3 (2024) : 912-922 . |
| APA | Zhang, Chun-Yang , Yao, Hong-Yu , Chen, C. L. Philip , Lin, Yue-Na . Graph Representation Learning via Contrasting Cluster Assignments . | IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS , 2024 , 16 (3) , 912-922 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Graph representation learning has recently garnered significant attention due to its wide applications in graph analysis tasks. It is well-known that real -world networks are dynamic, with edges and nodes evolving over time. This presents unique challenges that are distinct from those of static networks. However, most graph representation learning methods are either designed for static graphs, or address only partial challenges associated with dynamic graphs. They overlook the intricate interplay between topology and temporality in the evolution of dynamic graphs and the complexity of sequence modeling. Therefore, we propose a new dynamic graph representation learning model, called as R-GraphSAGE, which takes comprehensive considerations for embedding dynamic graphs. By incorporating a recurrent structure into GraphSAGE, the proposed RGraphSAGE explores structural and temporal patterns integrally to capture more fine-grained evolving patterns of dynamic graphs. Additionally, it offers a lightweight architecture to decrease the computational costs for handling snapshot sequences, achieving a balance between performance and complexity. Moreover, it can inductively process the addition of new nodes and adapt to the situations without labels and node attributes. The performance of the proposed R-GraphSAGE is evaluated across various downstream tasks with both synthetic and real -world networks. The experimental results demonstrate that it outperforms state-of-the-art baselines by a significant margin in most cases.
Keyword ：
Dynamic networks Dynamic networks Graph representation learning Graph representation learning Inductive learning Inductive learning Recurrent graph neural networks Recurrent graph neural networks Unsupervised learning Unsupervised learning
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Yao, Hong-Yu , Zhang, Chun-Yang , Yao, Zhi-Liang et al. A recurrent graph neural network for inductive representation learning on dynamic graphs [J]. | PATTERN RECOGNITION , 2024 , 154 . |
| MLA | Yao, Hong-Yu et al. "A recurrent graph neural network for inductive representation learning on dynamic graphs" . | PATTERN RECOGNITION 154 (2024) . |
| APA | Yao, Hong-Yu , Zhang, Chun-Yang , Yao, Zhi-Liang , Chen, C. L. Philip , Hu, Junfeng . A recurrent graph neural network for inductive representation learning on dynamic graphs . | PATTERN RECOGNITION , 2024 , 154 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
针对现有课程群在综合实践教学上存在知识点零散、内容重叠、实践路径单一、缺乏有效评价等问题，提出一种基于知识图谱的“能力导向+问题驱动”综合性实践教学模式，分别从教学目标、问题分解、资源整合、实施方式和成绩评定等方面探讨多路径实践教学及评定方法。
Keyword ：
机器学习课程群 机器学习课程群 知识图谱 知识图谱 综合实践 综合实践 能力导向 能力导向 问题驱动 问题驱动
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 陈飞 , 张春阳 , 于元隆 . 基于知识图谱的综合实践教学设计 [J]. | 计算机教育 , 2023 , 5 (04) : 158-162 . |
| MLA | 陈飞 et al. "基于知识图谱的综合实践教学设计" . | 计算机教育 5 . 04 (2023) : 158-162 . |
| APA | 陈飞 , 张春阳 , 于元隆 . 基于知识图谱的综合实践教学设计 . | 计算机教育 , 2023 , 5 (04) , 158-162 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
In recent years, graph neural network has become the main paradigm for solving graph analysis tasks, which can easily process high-dimensional data and has a powerful fitting capability. Recent works on graph neural networks have successfully transferred the convolution network in computer vision to graph. Graph convolution network (GCN) has become the classical network framework in graph neural networks due to its simple aggregation approach and favorable theoretical support. When the original graph data are constructed, an adjacency matrix is used to represent the topology, where 0 or 1 indicates whether there is a connection between nodes. Moreover, GCN aggregates node attributes only depends on adjacency matrix. Although it can learn a mapping function, its message propagation mechanism is fixed for a given adjacency matrix. However, for specific downstream tasks, we expect to propagate messages relevant to the downstream task, while a fixed aggregation mode cannot handle this. To this end, we propose a graph convolution neural network with a learnable message propagation mechanism. The original adjacency matrix is adjusted through a learnable weight, so that the message propagation mechanism better adapts to downstream tasks. Experimental results show that the proposed model achieves significant performance in node classification. © 2023 IEEE.
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Cai, H.-C. , Lin, Y.-N. , Zhang, C.-Y. . Graph Convolutional Network with Learnable Message Propagation Mechanism [未知]. |
| MLA | Cai, H.-C. et al. "Graph Convolutional Network with Learnable Message Propagation Mechanism" [未知]. |
| APA | Cai, H.-C. , Lin, Y.-N. , Zhang, C.-Y. . Graph Convolutional Network with Learnable Message Propagation Mechanism [未知]. |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Graphs have become a widely-used tool to model data with relationships in real life for a long time. To discover the important contents in the graph, many graph neural networks (GNNs) have been come up with. Nevertheless, these models tend to adopt ReLU as their activation function for its nonlinearity, effectiveness, and efficiency. Owing to its own deficiency, it would cause many generated feature elements to be zero, which would miss part significant features. To overcome this problem, an adaptive weight vector to tune the features was provided. By limiting the elements of the weight vector, it can be a better substitute for ReLU. Besides, such a weight vector adaptively measures the importance of each feature element to work as a feature selection operator. To show the function of the weight vector, we examine a GCN with the weight vecotor in node classification, and it exhibits overall improvements over three well-known citation networks. © 2023 IEEE.
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Lin, Y.-N. , Zhang, C.-Y. . Adaptive Feature Selection on Graph [未知]. |
| MLA | Lin, Y.-N. et al. "Adaptive Feature Selection on Graph" [未知]. |
| APA | Lin, Y.-N. , Zhang, C.-Y. . Adaptive Feature Selection on Graph [未知]. |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Exploring dynamic patterns from complex and large-scale networks is a significant and challenging task in graph analysis. One of the most advanced solutions is dynamic graph representation learning, which embeds structural and temporal correlations into a representative vector for each node or subgraph. Existing models have made some successes, such as overcoming the problems of induction for unseen nodes and scalability for large-scale evolving networks. However, these models usually rely on crisp representation learning that is incapable of modeling feature fuzziness and capturing uncertainties in dynamic graphs. While real-world dynamic networks as complex systems always contain non-negligible but inestimable uncertainties in node/link attributes and network topology. These uncertainties may cause the learned representations from crisp models hard to precisely reflect network evolution. To address the issues, we propose a new dynamic graph representation learning model, called FuzzyDGL, which first incorporates fuzzy representation learning to handle the uncertainties in dynamic graphs. Through combining CDGRL with fuzzy logic, the FuzzyDGL digests both of their advantages. On the one hand, it has flexible model scalability and brilliant inductive capability. On the other hand, it can model feature fuzziness to reduce the impact of uncertainties in dynamic graphs, improving the quality of learned representations. To demonstrate its effectiveness, we conduct two important tasks of network analysis, including link prediction and node classification, over eight real-world datasets. The experimental results show the strong competitiveness and generalization of the FuzzyDGL against a number of baseline models.
Keyword ：
Computational modeling Computational modeling Dynamic graph Dynamic graph dynamics modeling dynamics modeling fuzzy representation fuzzy representation Fuzzy systems Fuzzy systems graph representation learning graph representation learning Network topology Network topology Representation learning Representation learning Social networking (online) Social networking (online) Task analysis Task analysis Uncertainty Uncertainty
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Yao, Hong-Yu , Yu, Yuan-Long , Zhang, Chun-Yang et al. Fuzzy Representation Learning on Dynamic Graphs [J]. | IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS , 2023 . |
| MLA | Yao, Hong-Yu et al. "Fuzzy Representation Learning on Dynamic Graphs" . | IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS (2023) . |
| APA | Yao, Hong-Yu , Yu, Yuan-Long , Zhang, Chun-Yang , Lin, Yue-Na , Li, Shang-Jia . Fuzzy Representation Learning on Dynamic Graphs . | IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS , 2023 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
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 (CNNs) and processed by a multilayer perceptron (MLP) to generate the ultimate trajectories. Finally, to illustrate the effectiveness of the STSDGNN 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 cuttingedge models. The visualization results intuitively explain that our method can extract sophisticated and subtle multivehicle interactions, resulting in accurate predictions.
Keyword ：
~Autonomous driving ~Autonomous driving dynamic graph dynamic graph graph neural network (GNN) graph neural network (GNN) spatial-temporal dependencies spatial-temporal dependencies vehicle trajectory prediction vehicle trajectory prediction
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Li, Feng-Jie , Zhang, Chun-Yang , Chen, C. L. Philip . STS-DGNN: Vehicle Trajectory Prediction via Dynamic Graph Neural Network With Spatial-Temporal Synchronization [J]. | IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT , 2023 , 72 . |
| MLA | Li, Feng-Jie et al. "STS-DGNN: Vehicle Trajectory Prediction via Dynamic Graph Neural Network With Spatial-Temporal Synchronization" . | IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 72 (2023) . |
| APA | Li, Feng-Jie , Zhang, Chun-Yang , Chen, C. L. Philip . STS-DGNN: Vehicle Trajectory Prediction via Dynamic Graph Neural Network With Spatial-Temporal Synchronization . | IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT , 2023 , 72 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Semi-supervised learning is a common way that investigates how to improve performance of a visual learning model, while data annotation is far from sufficient. Recent works in semi-supervised deep learning have successfully applied consistency regularization, which encourages a model to maintain consistent predictions for different perturbed versions of an image. However, most of such methods ignore the category correlation of image features, especially when exploiting strong augmentation methods for unlabeled images. To address this problem, we propose PConMatch, a model that leverages a probabilistic contrastive learning framework to separate the features of strongly-augmented versions from different classes. A semi-supervised probabilistic contrastive loss is designed, which takes both labeled and unlabeled samples into account and develops an auxiliary module to generate a probability score to measure the model prediction confidence for each sample. Specifically, PConMatch first generates a pair of weakly-augmented versions for each labeled sample, and produces a weakly-augmented version and a corresponding pair of strongly-augmented versions for each unlabeled sample. Second, a probability score module is proposed to assign pseudo-labeling confidence scores to strongly-augmented unlabeled images. Finally, the probability score of each sample is further passed to the contrastive loss, combining with consistency regularization to enable the model to learn better feature representations. Extensive experiments on four publicly available image classification benchmarks demonstrate that the proposed approach achieves state-of-the-art performance in image classification. Several rigorous ablation studies are conducted to validate the effectiveness of the method.
Keyword ：
Annotations Annotations consistency regularization consistency regularization contrastive learning contrastive learning data augmen- tation data augmen- tation image classification image classification Image classification Image classification Predictive models Predictive models Probabilistic logic Probabilistic logic Pseudo-labeling Pseudo-labeling Semantics Semantics Semi-supervised learning Semi-supervised learning Task analysis Task analysis Visualization Visualization
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Lin, Huibin , Zhang, Chun-Yang , Wang, Shiping et al. A Probabilistic Contrastive Framework for Semi-Supervised Learning [J]. | IEEE TRANSACTIONS ON MULTIMEDIA , 2023 , 25 : 8767-8779 . |
| MLA | Lin, Huibin et al. "A Probabilistic Contrastive Framework for Semi-Supervised Learning" . | IEEE TRANSACTIONS ON MULTIMEDIA 25 (2023) : 8767-8779 . |
| APA | Lin, Huibin , Zhang, Chun-Yang , Wang, Shiping , Guo, Wenzhong . A Probabilistic Contrastive Framework for Semi-Supervised Learning . | IEEE TRANSACTIONS ON MULTIMEDIA , 2023 , 25 , 8767-8779 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Self-supervised graph representation learning (GRL) has shown great success in scientific research and real-world applications. Nevertheless, one obstacle in GRL is the demand for graph augmentation (GA), which deeply impacts the representation qualities. On the one hand, GA supplements the data amount and enhances the robustness and quality of the representations. On the other hand, collocating appropriate augmentations claims nontrivial attempts. In this article, a new method to free GA is provided building a novel fuzzy view and two crisp views of the original graph. As all the views are transformed from the original graph, they are semantically similar and naturally considered to possess high-quality positive samples. In this way, the data amount is compensated to a degree without changing the raw node attributes or graph topology. Additionally, to ensure the diversity of the positives, asymmetric renormalization and noise perturbation are adopted. Experiments toward node-level tasks on several real-world datasets demonstrate the competition against several state-of-the-art models.
Keyword ：
Fuzzy representation Fuzzy representation graph augmentation graph augmentation graph representation learning graph representation learning self-supervised learning self-supervised learning
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Lin, Yue-Na , Cai, Hai-Chun , Zhang, Chun-Yang et al. Multiple Views to Free Graph Augmentations [J]. | IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS , 2023 . |
| MLA | Lin, Yue-Na et al. "Multiple Views to Free Graph Augmentations" . | IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS (2023) . |
| APA | Lin, Yue-Na , Cai, Hai-Chun , Zhang, Chun-Yang , Chen, C. L. Philip . Multiple Views to Free Graph Augmentations . | IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS , 2023 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Unsupervised person re-identification (Re-ID) is more substantial than the supervised one because it does not require any labeled samples. Currently, the most advanced unsupervised Re-ID models generate pseudo-labels to group images into different clusters and then establish a memory bank to calculate contrastive loss between instances and clusters. This framework has been proven to be remarkably efficient for unsupervised person Re-ID tasks. However, clustering operation inevitably produces misclassification, which brings noises and difficulties to contrastive learning and affects the initialization and updating of the prototype features stored in the memory bank. To solve this problem, we propose a new robust unsupervised person Re-ID model with two developed modules: Cluster Sample Aggregation module (CSA) and Hard Positive Sampling strategy (HPS). The CSA module aggregates each sample in the same cluster through the multi-head self-attention mechanism. This process enables the initialization of prototypes based on the similarities observed within clusters. Additionally, the HPS strategy extracts the dispersion degree of each sample by means of a self-attention aggregation module (SAA) that has been trained by CSA module. According to the obtained indicators, the hardest positive sample is sampled to update the prototype feature stored in the memory bank. With the self-attention mechanism fusing the information among instances in each cluster, the implicit relationships between samples can be better explored in a more refined way. Experiments show that our method achieves state-of-the-art results against existing unsupervised baselines on Market-1501, PersonX, and MSMT17 datasets.
Keyword ：
Contrastive learning Contrastive learning Person Re-ID Person Re-ID Self-attention Self-attention Unsupervised learning Unsupervised learning
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Lin, Huibin , Fu, Hai-Tao , Zhang, Chun-Yang et al. A new robust contrastive learning for unsupervised person re-identification [J]. | INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS , 2023 , 15 (5) : 1779-1793 . |
| MLA | Lin, Huibin et al. "A new robust contrastive learning for unsupervised person re-identification" . | INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS 15 . 5 (2023) : 1779-1793 . |
| APA | Lin, Huibin , Fu, Hai-Tao , Zhang, Chun-Yang , Chen, C. L. Philip . A new robust contrastive learning for unsupervised person re-identification . | INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS , 2023 , 15 (5) , 1779-1793 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Export
| Results： |
Selected to |
| Format： |
