Yue-Na Lin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yue-Na Lin has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Chun-Yang Zhang
College of Computer and Data Science, Fuzhou University, Fuzhou, China
7 shared publications - Chun Lung Philip Chen
South China University of Technology
5 shared publications - Hai-Chun Cai
School of Computer and Data Science, Fuzhou University, Fuzhou, China
5 shared publications - Hong-Yu Yao
College of Computer and Data Science, Fuzhou University, Fuzhou, China
4 shared publications Wu-Peng Fang
School of Computer and Data Science, Fuzhou University, Fuzhou, China
2 shared publications- Deng-Bao Wang
School of Computer Science and Engineering, Southeast University, Nanjing, China
1 shared publication
Latest Publications
- 1 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 37 (10) , 6159-6172
Simplified Graph Contrastive Learning Model Without Augmentation
- 1 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 37 (10) , 6159-6172
Simplified Graph Contrastive Learning Model Without Augmentation
- 25 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Fuzzy Systems
- Vol. 32 (9) , 5259-5271
Fuzzy Neural Network for Representation Learning on Uncertain Graphs
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.
- 25 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Fuzzy Systems
- Vol. 32 (9) , 5259-5271
Fuzzy Neural Network for Representation Learning on Uncertain Graphs
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.
- 4 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. 11 (3) , 3920-3930
Multiple Views to Free Graph Augmentations
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.
- 4 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Social Systems
- Vol. 11 (3) , 3920-3930
Multiple Views to Free Graph Augmentations
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.
- 17 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Systems, Man, and Cybernetics: Systems
- Vol. 54 (2) , 878-890
Fuzzy Representation Learning on Dynamic Graphs
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 acrlong 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.
- 17 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Systems, Man, and Cybernetics: Systems
- Vol. 54 (2) , 878-890
Fuzzy Representation Learning on Dynamic Graphs
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 acrlong 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.
- 8 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive and Developmental Systems
- Vol. 16 (3) , 912-922
Graph Representation Learning via Contrasting Cluster Assignments
With the rise of contrastive learning, unsupervised graph representation learning 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 graph representation learning models pay attention to topological proximity, assuming that nodes that are closer in graph topology are more similar. However, in 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 graph representation learning model by contrasting cluster assignments, called GRCCA. To comprehensively explore the global and local views, it combines multi-view 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.
- 8 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive and Developmental Systems
- Vol. 16 (3) , 912-922
Graph Representation Learning via Contrasting Cluster Assignments
With the rise of contrastive learning, unsupervised graph representation learning 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 graph representation learning models pay attention to topological proximity, assuming that nodes that are closer in graph topology are more similar. However, in 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 graph representation learning model by contrasting cluster assignments, called GRCCA. To comprehensively explore the global and local views, it combines multi-view 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.
- 2 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 7, 41-44
Adaptive Feature Selection on Graph
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.
- 2 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 7, 41-44
Adaptive Feature Selection on Graph
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.
- 6 March 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Fuzzy Systems
- Vol. 31 (10) , 3358-3370
Fuzzy Representation Learning on Graph
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.
- 6 March 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Fuzzy Systems
- Vol. 31 (10) , 3358-3370
Fuzzy Representation Learning on Graph
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.
- 25 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 10 (4) , 2074-2085
Graph Representation Learning With Adaptive Metric
Contrastive learning has been widely used in graph representation learning, which extracts node or graph representations by contrasting positive and negative node pairs. It requires node representations (embeddings) to reflect their correlations in topology, increasing the similarities between an anchor node and its positive nodes, or reducing the similarities with its negative nodes in embedding space. However, most existing contrastive models measure similarities through a fixed metric that equally scores all sample pairs in a specific feature space, but ignores the varieties of node attributes and network topologies. Moreover, these fixed metrics are always defined explicitly and manually, which makes them unsuitable for applying to all graphs and networks. To solve these problems, we propose a novel graph representation learning model with an adaptive metric, called GRAM, which produces appropriate similarity scores of node pairs according to the different significance of each dimension in their embedding vectors and adaptive metrics based on data distribution. With these scores, it is better to train a graph encoder and obtain representative embeddings. Experimental results show that GRAM has strong competitiveness in multiple tasks.
- 25 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Network Science and Engineering
- Vol. 10 (4) , 2074-2085
Graph Representation Learning With Adaptive Metric
Contrastive learning has been widely used in graph representation learning, which extracts node or graph representations by contrasting positive and negative node pairs. It requires node representations (embeddings) to reflect their correlations in topology, increasing the similarities between an anchor node and its positive nodes, or reducing the similarities with its negative nodes in embedding space. However, most existing contrastive models measure similarities through a fixed metric that equally scores all sample pairs in a specific feature space, but ignores the varieties of node attributes and network topologies. Moreover, these fixed metrics are always defined explicitly and manually, which makes them unsuitable for applying to all graphs and networks. To solve these problems, we propose a novel graph representation learning model with an adaptive metric, called GRAM, which produces appropriate similarity scores of node pairs according to the different significance of each dimension in their embedding vectors and adaptive metrics based on data distribution. With these scores, it is better to train a graph encoder and obtain representative embeddings. Experimental results show that GRAM has strong competitiveness in multiple tasks.