Xu Yuan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xu Yuan has a total of 30 co-authors. Here are the top co-authors by number of shared publications:
- Liang Zhao
Dalian University of Technology, Dalian, Liaoning, China
3 shared publications - Ruixin Ma
School of Software Technology, Dalian University of Technology, Dalian 116024, China
3 shared publications - Shuo Yu
School of Computer Science and Technology, Dalian University of Technology
3 shared publications - Zhikui Chen
School of Software Technology, Dalian University of Technology, Dalian, China
3 shared publications - Feng Ding
Dalian University of Technology, Dalian, China
2 shared publications - Shaokui Gu
Shanghai Key Lab of Intelligent Information Processing, College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, China
2 shared publications
Latest Publications
- Open Access
Explicit and Implicit Feature Contrastive Learning Model for Knowledge Graph Link Prediction
Knowledge graph link prediction is crucial for constructing triples in knowledge graphs, which aim to infer whether there is a relation between the entities. Recently, graph neural networks and contrastive learning have demonstrated superior performance compared with traditional translation-based models; they successfully extracted common features through explicit linking between entities. However, the implicit associations between entities without a linking relationship are ignored, which impedes the model from capturing distant but semantically rich entities. In addition, directly applying contrastive learning based on random node dropout to link prediction tasks, or limiting it to triplet-level, leads to constrained model performance. To address these challenges, we design an implicit feature extraction module that utilizes the clustering characteristics of latent vector space to find entities with potential associations and enrich entity representations by mining similar semantic features from the conceptual level. Meanwhile, the subgraph mechanism is introduced to preserve the structural information of explicitly connected entities. Implicit semantic features and explicit structural features serve as complementary information to provide high-quality self-supervised signals. Experiments are conducted on three benchmark knowledge graph datasets. The results validate that our model outperforms the state-of-the-art baselines in link prediction tasks.
Open AccessExplicit and Implicit Feature Contrastive Learning Model for Knowledge Graph Link Prediction
Knowledge graph link prediction is crucial for constructing triples in knowledge graphs, which aim to infer whether there is a relation between the entities. Recently, graph neural networks and contrastive learning have demonstrated superior performance compared with traditional translation-based models; they successfully extracted common features through explicit linking between entities. However, the implicit associations between entities without a linking relationship are ignored, which impedes the model from capturing distant but semantically rich entities. In addition, directly applying contrastive learning based on random node dropout to link prediction tasks, or limiting it to triplet-level, leads to constrained model performance. To address these challenges, we design an implicit feature extraction module that utilizes the clustering characteristics of latent vector space to find entities with potential associations and enrich entity representations by mining similar semantic features from the conceptual level. Meanwhile, the subgraph mechanism is introduced to preserve the structural information of explicitly connected entities. Implicit semantic features and explicit structural features serve as complementary information to provide high-quality self-supervised signals. Experiments are conducted on three benchmark knowledge graph datasets. The results validate that our model outperforms the state-of-the-art baselines in link prediction tasks.
- 16 August 2024
- Published by Elsevier in Expert Systems with Applications
- Vol. 257
Knowledge graph fine-grained network with attribute transfer for recommendation
- 16 August 2024
- Published by Elsevier in Expert Systems with Applications
- Vol. 257
Knowledge graph fine-grained network with attribute transfer for recommendation
- 8 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 70 (1) , 3709-3721
Few-Shot Semantic Segmentation for Consumer Electronics: An Inter-Class Relation Mining Approach
Few-shot semantic segmentation (FSS), which can perform segmentation using only a limited number of annotated examples, is a promising technique that has been embedded in many electronic products. Existing approaches usually achieve segmentation for the query image by computing the similarity between the support and query images. However, when segmenting a new query image, the model prediction may be interfered with by distinct classes with similar semantic information, leading to unsatisfactory results. This may greatly weaken the generalization of FSS in real-world scenarios. In response to this challenge, we propose a few-shot semantic segmentation model based on inter-class relation mining named IRMNet. Firstly, we devise a class filter module that accurately selects useful semantic information by mining the class relations between the query and support images. Then, we use a class generation module that applies a diffusion model to generate rough segmentation masks for query images to augment supervision signals. Finally, we conduct extensive experiments on the PASCAL-5i and FSS-1000 datasets. The evaluation results show that IRMNet can achieve superior performance compared to other baselines. The advancement of FSS in this work can contribute to enhancing visual intelligence in real-world consumer electronics.
- 8 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 70 (1) , 3709-3721
Few-Shot Semantic Segmentation for Consumer Electronics: An Inter-Class Relation Mining Approach
Few-shot semantic segmentation (FSS), which can perform segmentation using only a limited number of annotated examples, is a promising technique that has been embedded in many electronic products. Existing approaches usually achieve segmentation for the query image by computing the similarity between the support and query images. However, when segmenting a new query image, the model prediction may be interfered with by distinct classes with similar semantic information, leading to unsatisfactory results. This may greatly weaken the generalization of FSS in real-world scenarios. In response to this challenge, we propose a few-shot semantic segmentation model based on inter-class relation mining named IRMNet. Firstly, we devise a class filter module that accurately selects useful semantic information by mining the class relations between the query and support images. Then, we use a class generation module that applies a diffusion model to generate rough segmentation masks for query images to augment supervision signals. Finally, we conduct extensive experiments on the PASCAL-5i and FSS-1000 datasets. The evaluation results show that IRMNet can achieve superior performance compared to other baselines. The advancement of FSS in this work can contribute to enhancing visual intelligence in real-world consumer electronics.
- 27 February 2024
- Published by Springer Nature
- p. 349-367
Query Optimization Mechanism for Blockchain-Based Efficient Data Traceability
- 27 February 2024
- Published by Springer Nature
- p. 349-367
Query Optimization Mechanism for Blockchain-Based Efficient Data Traceability
- Open Access
- 31 January 2024
- Published by MDPI AG in Mathematics
- Vol. 12 (3) , 450
Semantic-Enhanced Knowledge Graph Completion
Knowledge graphs (KGs) serve as structured representations of knowledge, comprising entities and relations. KGs are inherently incomplete, sparse, and have a strong need for completion. Although many knowledge graph embedding models have been designed for knowledge graph completion, they predominantly focus on capturing observable correlations between entities. Due to the sparsity of KGs, potential semantic correlations are challenging to capture. To tackle this problem, we propose a model entitled semantic-enhanced knowledge graph completion (SE-KGC). SE-KGC effectively addresses the issue by incorporating predefined semantic patterns, enabling the capture of semantic correlations between entities and enhancing features for representation learning. To implement this approach, we employ a multi-relational graph convolution network encoder, which effectively encodes the KG. Subsequently, we utilize a scoring decoder to evaluate triplets. Experimental results demonstrate that our SE-KGC model outperforms other state-of-the-art methods in link-prediction tasks across three datasets. Specifically, compared to the baselines, SE-KGC achieved improvements of 11.7%, 1.05%, and 2.30% in terms of MRR on these three datasets. Furthermore, we present a comprehensive analysis of the contributions of different semantic patterns, and find that entities with higher connectivity play a pivotal role in effectively capturing and characterizing semantic information.
- 31 January 2024
- Published by MDPI AG in Mathematics
- Vol. 12 (3) , 450
Open AccessSemantic-Enhanced Knowledge Graph Completion
Knowledge graphs (KGs) serve as structured representations of knowledge, comprising entities and relations. KGs are inherently incomplete, sparse, and have a strong need for completion. Although many knowledge graph embedding models have been designed for knowledge graph completion, they predominantly focus on capturing observable correlations between entities. Due to the sparsity of KGs, potential semantic correlations are challenging to capture. To tackle this problem, we propose a model entitled semantic-enhanced knowledge graph completion (SE-KGC). SE-KGC effectively addresses the issue by incorporating predefined semantic patterns, enabling the capture of semantic correlations between entities and enhancing features for representation learning. To implement this approach, we employ a multi-relational graph convolution network encoder, which effectively encodes the KG. Subsequently, we utilize a scoring decoder to evaluate triplets. Experimental results demonstrate that our SE-KGC model outperforms other state-of-the-art methods in link-prediction tasks across three datasets. Specifically, compared to the baselines, SE-KGC achieved improvements of 11.7%, 1.05%, and 2.30% in terms of MRR on these three datasets. Furthermore, we present a comprehensive analysis of the contributions of different semantic patterns, and find that entities with higher connectivity play a pivotal role in effectively capturing and characterizing semantic information.
- Open Access
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 3609-3618
MVCIR-net: Multi-view Clustering Information Reinforcement Network
Multi-view clustering (MVC) integrates information from different views to improve clustering performance compared to single-view clustering. However, the raw multi-view data in the feature space often contains irrelevant information to the clustering task, which is difficult to separate using existing methods. This irrelevant information is processed equally with clustering information, negatively impacting the final clustering performance. In this paper, we propose a new framework for multi-view clustering information reinforcement network (MVCIR-net) to alleviate these problems. Our method gives practical clustering meaning to the clustering distribution layer by contrastive learning. Then, the trusted neighbor instances distribution of the normalized graph is debias aggregated to form the clustering information propensity distribution, and the clustering information distribution is made to fit this distribution. In addition, the coupling degree of the clustering information distribution in different views on the same sample should be enhanced. Through the aforementioned strategies, the raw data is fuzzy mapped into clustering information, and the network's ability to recognize clustering information is strengthened. Finally, the fuzzy mapping data is input into the network and reconstructed to evaluate the quality of the extracted clustering information. Extensive experiments on public multi-view datasets show that MVCIR-net achieves superior clustering effectiveness and the ability to identify clustering information.
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 3609-3618
Open AccessMVCIR-net: Multi-view Clustering Information Reinforcement Network
Multi-view clustering (MVC) integrates information from different views to improve clustering performance compared to single-view clustering. However, the raw multi-view data in the feature space often contains irrelevant information to the clustering task, which is difficult to separate using existing methods. This irrelevant information is processed equally with clustering information, negatively impacting the final clustering performance. In this paper, we propose a new framework for multi-view clustering information reinforcement network (MVCIR-net) to alleviate these problems. Our method gives practical clustering meaning to the clustering distribution layer by contrastive learning. Then, the trusted neighbor instances distribution of the normalized graph is debias aggregated to form the clustering information propensity distribution, and the clustering information distribution is made to fit this distribution. In addition, the coupling degree of the clustering information distribution in different views on the same sample should be enhanced. Through the aforementioned strategies, the raw data is fuzzy mapped into clustering information, and the network's ability to recognize clustering information is strengthened. Finally, the fuzzy mapping data is input into the network and reconstructed to evaluate the quality of the extracted clustering information. Extensive experiments on public multi-view datasets show that MVCIR-net achieves superior clustering effectiveness and the ability to identify clustering information.
- 24 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 30 (10709908) , 1422-1426
Mining Multi-View Clustering Space With Interpretable Space Search Constraint
Multi-view clustering can cluster signal samples from multiple views into groups. Currently, multi-view clustering fuses the information of different views into a low-dimensional space for clustering. However, the direct reduction of high-dimensional information to a very low-dimensional space leads to the loss of a lot of sample semantic information, while a higher dimension after dimensionality reduction may blur the clustering structure of samples. To tackle these problems, we propose a novel framework called Mining Multi-view Clustering Space with Interpretable Space Search Constraint to explore the clustering structure while preserving the low-dimensional space semantic information. Our method maps samples from the raw space to a low-dimensional space separated into consensus and private features. This allows us to explore the interpretability of samples in the low-dimensional space to achieve representative representations. After assembling these representations, guided fusion is carried out and a search constraint is imposed to achieve a more reasonable clustering structure. Finally, by dynamically screening positive and negative samples, the clustering performance of the clustering space is maximized by contrastive learning. Extensive experiments on public datasets demonstrate that our method achieves state-of-the-art clustering effectiveness.
- 24 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 30 (10709908) , 1422-1426
Mining Multi-View Clustering Space With Interpretable Space Search Constraint
Multi-view clustering can cluster signal samples from multiple views into groups. Currently, multi-view clustering fuses the information of different views into a low-dimensional space for clustering. However, the direct reduction of high-dimensional information to a very low-dimensional space leads to the loss of a lot of sample semantic information, while a higher dimension after dimensionality reduction may blur the clustering structure of samples. To tackle these problems, we propose a novel framework called Mining Multi-view Clustering Space with Interpretable Space Search Constraint to explore the clustering structure while preserving the low-dimensional space semantic information. Our method maps samples from the raw space to a low-dimensional space separated into consensus and private features. This allows us to explore the interpretability of samples in the low-dimensional space to achieve representative representations. After assembling these representations, guided fusion is carried out and a search constraint is imposed to achieve a more reasonable clustering structure. Finally, by dynamically screening positive and negative samples, the clustering performance of the clustering space is maximized by contrastive learning. Extensive experiments on public datasets demonstrate that our method achieves state-of-the-art clustering effectiveness.
- Open Access
- 1 January 2021
- Published by Wiley in Wireless Communications and Mobile Computing
- Vol. 2021 (1)
Efficient Byzantine Consensus Mechanism Based on Reputation in IoT Blockchain
Blockchain technology has advanced rapidly in recent years and is now widely used in a variety of fields. Blockchain appears to be one of the best solutions for managing massive heterogeneous devices while achieving advanced data security and data reputation, particularly in the field of large‐scale IoT (Internet of Things) networks. Despite the numerous advantages, there are still challenges while deploying IoT applications on blockchain systems due to the limited storage, power, and computing capability of IoT devices, and some of these problems are caused by the consensus algorithm, which plays a significant role in blockchain systems by ensuring overall system reliability and robustness. Nonetheless, most existing consensus algorithms are prone to poor node reliability, low transaction per second (TPS) rates, and scalability issues. Aiming at some critical problems in the existing consensus algorithms, this paper proposes the Efficient Byzantine Reputation‐based Consensus (EBRC) mechanism to resolve the issues raised above. In comparison to traditional algorithms, we reinvented ways to evaluate node reliability and robustness and manage active nodes. Our experiments show that the EBRC algorithm has lower consensus delay, higher throughput, improved security, and lower verification costs. It offers new reference ideas for solving the Internet of Things+blockchain+Internet court construction problem.
- 1 January 2021
- Published by Wiley in Wireless Communications and Mobile Computing
- Vol. 2021 (1)
Open AccessEfficient Byzantine Consensus Mechanism Based on Reputation in IoT Blockchain
Blockchain technology has advanced rapidly in recent years and is now widely used in a variety of fields. Blockchain appears to be one of the best solutions for managing massive heterogeneous devices while achieving advanced data security and data reputation, particularly in the field of large‐scale IoT (Internet of Things) networks. Despite the numerous advantages, there are still challenges while deploying IoT applications on blockchain systems due to the limited storage, power, and computing capability of IoT devices, and some of these problems are caused by the consensus algorithm, which plays a significant role in blockchain systems by ensuring overall system reliability and robustness. Nonetheless, most existing consensus algorithms are prone to poor node reliability, low transaction per second (TPS) rates, and scalability issues. Aiming at some critical problems in the existing consensus algorithms, this paper proposes the Efficient Byzantine Reputation‐based Consensus (EBRC) mechanism to resolve the issues raised above. In comparison to traditional algorithms, we reinvented ways to evaluate node reliability and robustness and manage active nodes. Our experiments show that the EBRC algorithm has lower consensus delay, higher throughput, improved security, and lower verification costs. It offers new reference ideas for solving the Internet of Things+blockchain+Internet court construction problem.
- 1 November 2018
- Published by MIT Press in Neural Computation
- Vol. 30 (11) , 3128-3149
Cross-Entropy Pruning for Compressing Convolutional Neural Networks
The success of CNNs is accompanied by deep models and heavy storage costs. For compressing CNNs, we propose an efficient and robust pruning approach, cross-entropy pruning (CEP). Given a trained CNN model, connections were divided into groups in a group-wise way according to their corresponding output neurons. All connections with their cross-entropy errors below a grouping threshold were then removed. A sparse model was obtained and the number of parameters in the baseline model significantly reduced. This letter also presents a highest cross-entropy pruning (HCEP) method that keeps a small portion of weights with the highest CEP. This method further improves the accuracy of CEP. To validate CEP, we conducted the experiments on low redundant networks that are hard to compress. For the MNIST data set, CEP achieves an 0.08% accuracy drop required by LeNet-5 benchmark with only 16% of original parameters. Our proposed CEP also reduces approximately 75% of the storage cost of AlexNet on the ILSVRC 2012 data set, increasing the top-1 errorby only 0.4% and top-5 error by only 0.2%. Compared with three existing methods on LeNet-5, our proposed CEP and HCEP perform significantly better than the existing methods in terms of the accuracy and stability. Some computer vision tasks on CNNs such as object detection and style transfer can be computed in a high-performance way using our CEP and HCEP strategies. The success of CNNs is accompanied by deep models and heavy storage costs. For compressing CNNs, we propose an efficient and robust pruning approach, cross-entropy pruning (CEP). Given a trained CNN model, connections were divided into groups in a group-wise way according to their corresponding output neurons. All connections with their cross-entropy errors below a grouping threshold were then removed. A sparse model was obtained and the number of parameters in the baseline model significantly reduced. This letter also presents a highest cross-entropy pruning (HCEP) method that keeps a small portion of weights with the highest CEP. This method further improves the accuracy of CEP. To validate CEP, we conducted the experiments on low redundant networks that are hard to compress. For the MNIST data set, CEP achieves an 0.08% accuracy drop required by LeNet-5 benchmark with only 16% of original parameters. Our proposed CEP also reduces approximately 75% of the storage cost of AlexNet on the ILSVRC 2012 data set, increasing the top-1 errorby only 0.4% and top-5 error by only 0.2%. Compared with three existing methods on LeNet-5, our proposed CEP and HCEP perform significantly better than the existing methods in terms of the accuracy and stability. Some computer vision tasks on CNNs such as object detection and style transfer can be computed in a high-performance way using our CEP and HCEP strategies. The success of CNNs is accompanied by deep models and heavy storage costs. For compressing CNNs, we propose an efficient and robust pruning approach, cross-entropy pruning (CEP). Given a trained CNN model, connections were divided into groups in a group-wise way according to their corresponding output neurons. All connections with their cross-entropy errors below a grouping threshold were then removed. A sparse model was obtained and the number of parameters in the baseline model significantly reduced. This letter also presents a highest cross-entropy pruning (HCEP) method that keeps a small portion of weights with the highest CEP. This method further improves the accuracy of CEP. To validate CEP, we conducted the experiments on low redundant networks that are hard to compress. For the MNIST data set, CEP achieves an 0.08% accuracy drop required by LeNet-5 benchmark with only 16% of original parameters. Our proposed CEP also reduces approximately 75% of the storage cost of AlexNet on the ILSVRC 2012 data set, increasing the top-1 errorby only 0.4% and top-5 error by only 0.2%. Compared with three existing methods on LeNet-5, our proposed CEP and HCEP perform significantly better than the existing methods in terms of the accuracy and stability. Some computer vision tasks on CNNs such as object detection and style transfer can be computed in a high-performance way using our CEP and HCEP strategies.
- 1 November 2018
- Published by MIT Press in Neural Computation
- Vol. 30 (11) , 3128-3149
Cross-Entropy Pruning for Compressing Convolutional Neural Networks
The success of CNNs is accompanied by deep models and heavy storage costs. For compressing CNNs, we propose an efficient and robust pruning approach, cross-entropy pruning (CEP). Given a trained CNN model, connections were divided into groups in a group-wise way according to their corresponding output neurons. All connections with their cross-entropy errors below a grouping threshold were then removed. A sparse model was obtained and the number of parameters in the baseline model significantly reduced. This letter also presents a highest cross-entropy pruning (HCEP) method that keeps a small portion of weights with the highest CEP. This method further improves the accuracy of CEP. To validate CEP, we conducted the experiments on low redundant networks that are hard to compress. For the MNIST data set, CEP achieves an 0.08% accuracy drop required by LeNet-5 benchmark with only 16% of original parameters. Our proposed CEP also reduces approximately 75% of the storage cost of AlexNet on the ILSVRC 2012 data set, increasing the top-1 errorby only 0.4% and top-5 error by only 0.2%. Compared with three existing methods on LeNet-5, our proposed CEP and HCEP perform significantly better than the existing methods in terms of the accuracy and stability. Some computer vision tasks on CNNs such as object detection and style transfer can be computed in a high-performance way using our CEP and HCEP strategies. The success of CNNs is accompanied by deep models and heavy storage costs. For compressing CNNs, we propose an efficient and robust pruning approach, cross-entropy pruning (CEP). Given a trained CNN model, connections were divided into groups in a group-wise way according to their corresponding output neurons. All connections with their cross-entropy errors below a grouping threshold were then removed. A sparse model was obtained and the number of parameters in the baseline model significantly reduced. This letter also presents a highest cross-entropy pruning (HCEP) method that keeps a small portion of weights with the highest CEP. This method further improves the accuracy of CEP. To validate CEP, we conducted the experiments on low redundant networks that are hard to compress. For the MNIST data set, CEP achieves an 0.08% accuracy drop required by LeNet-5 benchmark with only 16% of original parameters. Our proposed CEP also reduces approximately 75% of the storage cost of AlexNet on the ILSVRC 2012 data set, increasing the top-1 errorby only 0.4% and top-5 error by only 0.2%. Compared with three existing methods on LeNet-5, our proposed CEP and HCEP perform significantly better than the existing methods in terms of the accuracy and stability. Some computer vision tasks on CNNs such as object detection and style transfer can be computed in a high-performance way using our CEP and HCEP strategies. The success of CNNs is accompanied by deep models and heavy storage costs. For compressing CNNs, we propose an efficient and robust pruning approach, cross-entropy pruning (CEP). Given a trained CNN model, connections were divided into groups in a group-wise way according to their corresponding output neurons. All connections with their cross-entropy errors below a grouping threshold were then removed. A sparse model was obtained and the number of parameters in the baseline model significantly reduced. This letter also presents a highest cross-entropy pruning (HCEP) method that keeps a small portion of weights with the highest CEP. This method further improves the accuracy of CEP. To validate CEP, we conducted the experiments on low redundant networks that are hard to compress. For the MNIST data set, CEP achieves an 0.08% accuracy drop required by LeNet-5 benchmark with only 16% of original parameters. Our proposed CEP also reduces approximately 75% of the storage cost of AlexNet on the ILSVRC 2012 data set, increasing the top-1 errorby only 0.4% and top-5 error by only 0.2%. Compared with three existing methods on LeNet-5, our proposed CEP and HCEP perform significantly better than the existing methods in terms of the accuracy and stability. Some computer vision tasks on CNNs such as object detection and style transfer can be computed in a high-performance way using our CEP and HCEP strategies.