检索结果-内蒙古大学图书馆

FHgraph:A Novel Framework for Fake News Detection Using graph contrastive learning and LLM

Computers, Materials & Continua 2025年第4期83卷 309-333页

作者： Yuanqing Li Mengyao Dai Sanfeng Zhang School of Cyber Science and Engineering Southeast UniversityNanjing210096China Key Laboratory of Computer Network and Information Integration(Southeast University) Ministry of EducationNanjing210096China

Social media has significantly accelerated the rapid dissemination of information,but it also boosts propagation of fake news,posing serious challenges to public awareness and social *** real-world contexts,the volume of trustable information far exceeds that of rumors,resulting in a class imbalance that leads models to prioritize the majority class during *** focus diminishes the model’s ability to recognize minority class ***,models may experience overfitting when encountering these minority samples,further compromising their generalization *** node-level classification tasks,fake news detection in social networks operates on graph-level samples,where traditional interpolation and oversampling methods struggle to effectively generate high-quality graph-level *** challenge complicates the identification of new instances of false *** address this issue,this paper introduces the FHgraph(Fake News Hunting graph)framework,which employs a generative data augmentation approach and a latent diffusion model to create graph structures that align with news communication *** the few-sample learning capabilities of large language models(LLMs),the framework generates diverse texts for minority class *** comprises a hierarchical multiview graph contrastive learning module,in which two horizontal views and three vertical levels are utilized for self-supervised learning,resulting in more optimized *** results show that FHgraph significantly outperforms state-of-the-art(SOTA)graph-level class imbalance methods and SOTA graph-level contrastive learning ***,FHgraph has achieved a 2%increase in F1 Micro and a 2.5%increase in F1 Macro in the PHEME dataset,as well as a 3.5%improvement in F1 Micro and a 4.3%improvement in F1 Macro on RumorEval dataset.

关键词： graph contrastive learning fake news detection data augmentation class imbalance LLM

来源：评论

学校读者我要写书评

暂无评论

TagRec: Temporal-Aware graph contrastive learning With Theoretical Augmentation for Sequential Recommendation

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 2025年第5期37卷 3015-3029页

作者： Peng, Tianhao Yuan, Haitao Zhang, Yongqi Li, Yuchen Dai, Peihong Wang, Qunbo Wang, Senzhang Wu, Wenjun Beihang Univ Beijing 100191 Peoples R China Nanyang Technol Univ Singapore 639798 Singapore Hong Kong Univ Sci & Technol Guangzhou Hong Kong Peoples R China Shanghai Jiao Tong Univ Shanghai 200240 Peoples R China Chinese Acad Sci Inst Automat Beijing 100045 Peoples R China Cent South Univ Changsha 410017 Hunan Peoples R China

Sequential recommendation systems aim to predict the future behaviors of users based on their historical interactions. Despite the success of neural architectures like Transformer and graph Neural Networks, these models often struggle with the inherent challenge of sparse data in accurately predicting future user behaviors. To alleviate the data sparsity problem, some methods leverage the contrastive learning to generate contrastive views, assuming the items appear discretely at the same time intervals and focusing on the sequence order. However, these approaches neglect the crucial temporal-aware collaborative patterns hidden within the user-item interactions, leading to a limited variety of contrastive pairs and less informative embeddings. The proposed framework, Temporal-aware graph contrastive learning with theoretical guarantees for sequential Recommendation (TagRec), integrates temporal-aware collaborative patterns with adaptive data augmentation to generate more informative user and item representations. TagRec employs a temporal-aware graph neural network to embed the original graph, then generates augmented graphs through the addition of interactions via latent user interest mining, the dropping of redundant interaction edges, and the perturbation of temporal information. Theoretical guarantees are provided that these augmentations enhance the graph's utility. Extensive experiments on real-world datasets demonstrate the superiority of the proposed approach over the state-of-the-art recommendation methods.

关键词： Collaboration Data models Recommender systems Data augmentation contrastive learning Adaptation models graph neural networks Analytical models Electronic mail Transformers Continuous-time sequential recommendation graph contrastive learning graph neural network data augmentation

来源：评论

学校读者我要写书评

暂无评论

Power system state estimation based on graph contrastive learning

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 270卷

作者： Li, Ping Dai, Zhen Wang, Mengzhen Wang, Zhenyu South China Univ Technol Sch Software Engn Guangzhou 510000 Guangdong Peoples R China China Southern Power Grid Artificial Intelligence Guangzhou 510000 Guangdong Peoples R China China Southern Power Grid Digital Grid Res Inst Co Guangzhou 510663 Guangdong Peoples R China

The efficient and stable operation of power systems relies on accurate state estimation. Traditional state estimation methods usually involve solving a minimization problem iteratively using Gauss-Newton methods, however, these methods still have some limitations, such as numerical instability and issues like the convergence time depending on the initial point. To solve the above problems, this paper proposes, for the first time, a data-driven state estimation model based on graph contrastive learning (GCLSE for short). Specifically, the model introduces the Bootstrapped Representation learning on graphs (BGRL) framework, effectively addressing the issue of large estimation errors in the presence of noise. We also propose a graph augmentation method using edge feature masking to preserve the topology of the power system. To comprehensively capture the features of nodes and edges in the power grid, the model introduces a novel hybrid encoder, which combines an Edge-Conditioned Convolutional Neural Network (ECC) with self-attention mechanisms and residual blocks, and a graph Convolutional Network (GCN) incorporating dynamic propagation strategies and gating mechanisms. The model proposes a dual optimization strategy combining contrastive loss and node state prediction loss, which optimizes model parameters while also improving state estimation accuracy. Experiments were conducted on the IEEE 39-bus system and the ACTIVSg2000 system using the base case and N-1 contingency topologies. Results show that the GCLSE model achieves lower estimation errors for voltage magnitude and voltage angle differences compared to existing benchmark models. The GCLSE model can also be used to provide abetter initial guess for the WLS method, which results in faster convergence as well as shorter computation time. Estimation error of the proposed methods meets the practical engineering requirements for state estimation and complies with the GBT standard's 2.5% error threshold.

关键词： graph contrastive learning State estimation graph Convolutional Network Edge-conditioned convolutional neural networks graph augmentation

来源：评论

学校读者我要写书评

暂无评论

GMNI: Achieve good data augmentation in unsupervised graph contrastive learning

引用

NEURAL NETWORKS 2025年 181卷 106804页

作者： Xiong, Xin Wang, Xiangyu Yang, Suorong Shen, Furao Zhao, Jian Nanjing Univ State Key Lab Novel Software Technol Nanjing 210023 Peoples R China Nanjing Univ Sch Artificial Intelligence Nanjing 210023 Peoples R China Nanjing Univ Dept Comp Sci & Technol Nanjing 210023 Peoples R China Nanjing Univ Sch Elect Sci & Engn Nanjing 210023 Peoples R China

graph contrastive learning (GCL) shows excellent potential in unsupervised graph representation learning. Data augmentation (DA), responsible for generating diverse views, plays a vital role in GCL, and its optimal choice heavily depends on the downstream task. However, it is impossible to measure task-relevant information under an unsupervised setting. Therefore, many GCL methods risk insufficient information by failing to preserve essential information necessary for the downstream task or risk encoding redundant information. In this paper, we propose a novel method called Minimal Noteworthy Information for unsupervised graph contrastive learning (GMNI), featuring automated DA. It achieves good DA by balancing missing and excessive information, approximating the optimal views in contrastive learning. We employ an adversarial training strategy to generate views that share minimal noteworthy information (MNI), reducing nuisance information by minimization optimization and ensuring sufficient information by emphasizing noteworthy information. Besides, we introduce randomness based on MNI to augmentation, thereby enhancing view diversity and stabilizing the model against perturbations. Extensive experiments on unsupervised and semi-supervised learning over 14 datasets demonstrate the superiority of GMNI over GCL methods with automated and manual DA. GMNI achieves up to a 1.64% improvement over the state-of-the-art in unsupervised node classification, up to a 1.97% improvement in unsupervised graph classification, and up to a 3.57% improvement in semi-supervised graph classification.

关键词： graph neural network graph contrastive learning Data augmentation

来源：评论

学校读者我要写书评

暂无评论

From overfitting to robustness: Quantity, quality, and variety oriented negative sample selection in graph contrastive learning

引用

APPLIED SOFT COMPUTING 2025年 170卷

作者： Ali, Adnan Li, Jinlong Chen, Huanhuan Bashir, Ali Kashif Univ Sci & Technol China Sch Comp Sci & Technol Jinzhai Rd 23006 Hefei Anhui Peoples R China Manchester Metropolitan Univ Dept Comp & Math Manchester M15 6BH England Chitkara Univ Chitkara Univ Inst Engn & Technol Ctr Res Impact & Outcome Rajpura 140401 Punjab India

graph contrastive learning (GCL) aims to contrast positive-negative counterparts to learn the node embeddings, whereas graph data augmentation methods are employed to generate these positive-negative samples. The quantity, quality, and variety of negative samples relative to positive samples play crucial roles in learning meaningful embeddings for node classification downstream tasks. Excessive quantity, low-quality, and less variation of negative samples cause the model to be overfitted for particular nodes, resulting in less robust models. To solve the overfitting problem in the GCL paradigm, this study proposes a novel Cumulative Sample Selection (CSS) algorithm by comprehensively considering the quantity, quality, and variety of negative samples. Initially, three negative sample pools are constructed: easy, medium, and hard negative samples, which contain 25%, 50%, and 25% of the total available negative samples, respectively. Later, 10% negative samples are selected from each of these three sample pools for training the model. After that, a decision agent module evaluates the model training results and decides whether to explore more negative samples from the three negative sample pools by increasing the ratio or to continue exploiting the current sampling ratio. The proposed algorithm is integrated into a proposed graph contrastive learning framework named NegAmplify (Negative samples Amplifi cation). NegAmplify is compared to the state-of-the-art methods on nine node classification datasets, with seven achieving better node classification accuracy with up to 2.86% improvement. The implementation of NegAmplify is available at https://***//mhadnanali/NegAmplify.

关键词： Self-supervised learning graph representation learning graph contrastive learning Negative sample selection Deep learning

来源：评论

学校读者我要写书评

暂无评论

Heterogeneous graph contrastive learning-based transductive health condition assessment of Francis turbine unit

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2025年 145卷

作者： Zhang, Fengyuan Liu, Jie Liu, Yujie Li, Yuxin Duan, Ran Chen, Zhidi Jiang, Xingxing Tongji Univ Sch Ocean & Earth Sci Shanghai 200092 Peoples R China Huazhong Univ Sci & Technol Sch Civil & Hydraul Engn Wuhan 430074 Peoples R China Changjiang Survey Planning Design & Res Co Ltd Wuhan 430010 Peoples R China CTG Wuhan Sci & Technol Innovat Pk Wuhan 430014 Peoples R China Soochow Univ Sch Rail Transportat Suzhou 215131 Peoples R China

To assess the Francis turbine unit's (FTU) degradation status from the onsite data without state labeling, a series of health benchmark model (HBM) driven health condition assessment (HCA) methods have been proposed. However, some limitation still exists, including: 1) Multiple similar HBMs are repeatedly constructed and trained to process multiple heterogeneous monitoring signals, however, there is a lack of a unified model that can handle the full task flow directly. 2) Simple linear methods are used to fuse multiple heterogeneous signals to construct performance degradation indexes (PDIs), ignoring temporal changes in the relationships within the signals and resulting in inadequate unit state representation. In this paper, a heterogeneous graph contrastive learning-based transductive health condition assessment of FTU considering multi-source monitoring signals is proposed. First, multi-source heterogeneous signals are converted into a series of heterogeneous signal graphs via the designed similarity-based edge-connection function considering the temporal representation differences. Then, an innovative graph-level heterogenous signal fusion method is proposed to represent unit conditions completely. By concatenating adjacency matrices of the heterogeneous signal graphs, multiple edge connections within the assessment period data are fused, obtaining a unique interactive graph with balanced and extended edge connections. Further, GCL-driven graph representator model is used to maximize the differences between the healthy and degraded interactive graph (IGs), and then the distances between the model readout vectors of the above two graphs is calculated as IPDIs, considering the signal correlations influenced by unit state changes. Verification experiments show that the proposed transductive HCA method effectively evaluates FTU's degradation without state labeling.

关键词： Francis turbine units Degradation assessment graph contrastive learning Heterogenous signals fusion Performance degradation index

来源：评论

学校读者我要写书评

暂无评论

AAGCN: An adaptive data augmentation for graph contrastive learning

引用

PATTERN RECOGNITION 2025年 163卷

作者： Qin, Peng Lu, Yaochun Chen, Weifu Li, Defang Feng, Guocan Sun Yat Sen Univ Sch Math Guangzhou Peoples R China Sun Yat Sen Univ Guangdong Prov Key Lab Guangzhou Peoples R China Guangzhou Maritime Univ Dept Comp Sci Guangzhou Peoples R China Guangzhou Vocat Coll Technol & Business Guangzhou Peoples R China

contrastive learning has achieved great success in many applications. A key step in contrastive learning is to find a positive sample and negative samples. Traditional methods find the positive sample by choosing the most similar sample. Amore popular approach is to do data augmentation where the original data and the augmented data are naturally treated as positive pairs. It is easy for grid data to do the augmentation, for example, we can rotate, crop or color an image to get augmented images. But it is challenging to do augmentation for graph data, due to non-Euclidean nature of graphs. Current graph augmentation methods mainly focus on masking nodes, dropping edges, or extracting subgraphs. Such methods lack of flexibility and require intensive manual settings. In this work, we propose a model called Adaptive Augmentation graph Convolutional Network (AAGCN) for semi-supervised node classification, based on adaptive graph augmentation. Rather than choose a probability distribution, for example, Bernoulli distribution, to drop some of the nodes or edges in Dropout, the proposed model learns the mask matrices for nodes or edges adaptively. Experiments on citation networks such as Cora, CiteSeer and Cora-ML show that AAGCN achieved state-ofthe-art performance compared with other popular graph neural networks. The proposed model was also tested on amore challenging and large-scale graph dataset, OGBN-Arxiv, which has 169,343 nodes and 1,166,243 edges. The proposed model could still achieve competitive prediction results.

关键词： graph augmentation graph contrastive learning graph semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Encoder augmentation for multi-task graph contrastive learning

引用

NEUROCOMPUTING 2025年 630卷

作者： Wang, Xiaoyu Zhang, Qiqi Liu, Gen Zhao, Zhongying Cui, Hongzhi Shandong Univ Sci & Technol Coll Comp Sci & Engn Qingdao 266590 Peoples R China Inspur Commun Informat Syst Co Jinan 250100 Peoples R China

graph contrastive learning (GCL), as one of the most popular self-supervised paradigms, has achieved a great deal of success in the field of graph representation learning. However, many GCL methods face a limitation in generating diverse enough views due to the absence of prior knowledge, leading to suboptimal performance. Moreover, the community structures are rarely considered. We argue that the semantic similarities among nodes within the same community substantially contribute to graph analyzing tasks. To address these issues, we propose an Encoder Augmentation for Multi-task graph contrastive learning method, known as EAMGCL. Specifically, we introduce a multi-layer information weighting aggregation method to enhance the diversity of the generated views within the encoder augmentation module. Additionally, we present a multitask graph contrastive learning module to discern local community information. The proposed EA-MGCL effectively captures and leverages node-level, node-community-level, and community-level information via three contrastive learning strategies. Extensive experimental results on six real-world datasets demonstrate that EA-MGCL achieves superior performance compared to state-of-the-art methods. The codes of this work are available at https://***/ZZY-graphMiningLab/EA-MGCL.

关键词： graph Neural Network graph contrastive learning Data augmentation graph analyzing task

来源：评论

学校读者我要写书评

暂无评论

Node importance evaluation in heterogeneous network based on attention mechanism and graph contrastive learning

引用

NEUROCOMPUTING 2025年 626卷

作者： Shu, Jian Zou, Yiling Cui, Hui Liu, Linlan Nanchang Hangkong Univ Sch Software Nanchang 330063 Peoples R China Nanchang Hangkong Univ Sch Informat Engn Nanchang 330063 Peoples R China

Recently, heterogeneous networks have attracted widespread attention as a modeling approach for complex networks. However, the complex structure and diversity of semantic relations of heterogeneous networks pose challenges to node importance evaluation. In addition, existing methods use SIR model to set true labels for all nodes, which increases the complexity. In light of this, this paper proposes anode importance evaluation in heterogeneous network based on attention mechanism and graph contrastive learning method(AGCL). Specifically, AGCL contains two core parts: node embedding and node importance evaluation. Considering the complex structure of heterogeneous networks, node embedding employs graph contrastive learning to comprehensively extract structural features through neighbor and cross-domain views. Node importance evaluation integrates an attention mechanism to calculate the global and local importance of nodes separately. To reduce the complexity of setting the true labels, a subset of nodes is sampled based on the power-law distribution of node degrees for model training. The evaluation of AGCL is conducted in three real-world networks utilizing three metrics: the maximum connected subgraph node ratio, the maximum propagation range in the linear threshold model, and the maximum propagation range in the independent cascade model. The experiment results demonstrate that AGCL outperforms state-of-the-art techniques in evaluating node importance.

关键词： Node importance Heterogeneous network graph contrastive learning Attention mechanism

来源：评论

学校读者我要写书评

暂无评论

MCTGCL: Mixed CNNTransformer for Mars Hyperspectral Image Classification With graph contrastive learning

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2025年 63卷

作者： Xi, Bobo Zhang, Yun Li, Jiaojiao Zheng, Tie Zhao, Xunfeng Xu, Haitao Xue, Changbin Li, Yunsong Chanussot, Jocelyn Xidian Univ Sch Telecommun Engn State Key Lab Integrated Serv Networks Xian Peoples R China Chinese Acad Sci Natl Space Sci Ctr Beijing 100190 Peoples R China Chinese Acad Sci Natl Space Sci Ctr Key Lab Elect & Informat Technol Space Syst Beijing 100190 Peoples R China Univ Grenoble Alpes Inria CNRS Grenoble INLJK F-38000 Grenoble France

Hyperspectral image (HSI) classification has been extensively studied in the context of Earth observation. However, its application in Mars exploration remains limited. Although convolutional neural networks (CNNs) have proven effective in HSI processing, their local receptive fields hinder their ability to capture long-range features. Transformers excel in global modeling and perform well in HSI classification (HSIC), but they often neglect the effective representation of local spectral and spatial features and tend to be more complex. To address these challenges, we propose a mixed CNN-transformer network for Mars HSI classification with graph contrastive learning to enhance classification performance. Specifically, we introduce an information-enhanced attention module (IEAM) designed to aggregate attention features from multiple perspectives. Additionally, we develop a lightweight dual-branch CNN-transformer (LDCT) network that efficiently extracts both local and global spectral-spatial features with lower complexity. To improve the discrimination of inter-class features, we apply graph contrastive learning to the topological structure of labeled samples. Furthermore, we annotated three Mars HSI datasets, referred to as HyMars, to validate the effectiveness of our proposed mixed CNN-"transformer network for Mars HSIC with graph contrastive learning (MCTGCL). Comprehensive experimental results across different amounts of labeled samples consistently demonstrate the superiority of the method.

关键词： Transformers Feature extraction Mars Minerals contrastive learning Hyperspectral imaging Convolutional neural networks Training Earth Data mining graph contrastive learning information-enhanced attention lightweight Mars exploration

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：